The following is a conversation with Don Song, a professor of computer science at UC Berkeley
with research interests and computer security, most recently with a focus on the intersection
between security and machine learning. This conversation was recorded before the outbreak
of the pandemic for everyone feeling the medical, psychological, and financial burden of this crisis.
I'm sending love your way. Stay strong. We're in this together. We'll beat this thing.
This is the Artificial Intelligence Podcast. If you enjoy it, subscribe on YouTube,
review it with 5 stars on Apple Podcasts, support on Patreon, or simply connect with me on Twitter
at Lex Freedman, spelled F-R-I-D-M-A-N. As usual, I'll do a few minutes of ads now
and never any ads in the middle that can break the flow of the conversation.
I hope that works for you. It doesn't hurt the listening experience.
This show is presented by Cash App, the number one finance app in the App Store.
When you get it, use code LEX Podcast. Cash App lets you send money to friends by Bitcoin
and invest in the stock market with as little as $1. Since Cash App does fractional share trading,
let me mention that the order execution algorithm that works behind the scenes
to create the abstraction of fractional orders is an algorithmic marvel.
So big props to the Cash App engineers for solving a hard problem that in the end provides an easy
interface that takes a step up to the next layer of abstraction over the stock market,
making trading more accessible for new investors and diversification much easier.
So again, if you get Cash App from the App Store, Google Play, and use the code LEX Podcast,
you get $10 and Cash App will also donate $10 to first, an organization that is helping to
advance robotics and STEM education for young people around the world.
And now here's my conversation with Dawn Song. Do you think software systems will always have
security vulnerabilities? Let's start at the broad, almost philosophical level.
That's a very good question. I mean, in general, right, it's very difficult to write completely
bug-free code and code that has no vulnerability and also especially given that the definition
of vulnerability is actually really broad. It's any type of attacks essentially on the code can,
you know, you can call that the cause by vulnerabilities.
And the nature of attacks is always changing as well? Like new ones are coming up?
Right. So for example, in the past, we talked about memory safety type of vulnerabilities
where essentially attackers can exploit the software and take over control of how the code
runs and then can launch attacks that way. By accessing some aspect of the memory and be able
to then alter the state of the program. Exactly. So for example, in the example of buffer overflow,
then the attacker essentially actually causes essentially unintended changes in the state
of the program. And then, for example, can then take over control flow of the program and let
the program to execute codes that actually the program didn't intend. So the attack can be a
remote attack. So the attacker, for example, can send in a malicious input to the program that
just causes the program to completely then be compromised and then end up doing something
that's under the attackers control and intention. But that's just one form of attacks and there
are other forms of attacks. Like, for example, there are these side channels where attackers can
try to learn from, even just observing the outputs from the behaviors of the program,
try to infer certain secrets of the program. So they essentially write the form of attacks is very
varied. It's very broad spectrum. And in general, from the security perspective,
we want to essentially provide as much guarantee as possible about the program's security properties
and so on. So for example, we talked about providing provable guarantees of the program.
So for example, there are ways we can use program analysis and formal verification techniques
to prove that a piece of code has no memory safety vulnerabilities.
What does that look like? What is that proof? Is that just a dream
for that's applicable to small case examples? Or is that possible to do for real world systems?
So actually, I mean, today I actually call it so we are entering the area of formally verified
systems. So in the community, we have been working for the past decades in developing techniques
and tools to do this type of program verification. And we have dedicated teams that have dedicated
their years or sometimes even decades of their work in the space. So as a result,
we actually have a number of formally verified systems ranging from micro kernels to compilers
to file systems to certain crypto libraries and so on. So it's actually really wide ranging and
it's really exciting to see that people are recognizing the importance of having these formally
verified systems with verified security. So that's great advancement that we see. But on the other
hand, I think we do need to take all these in essentially with caution as well in the sense that
just like I said, the type of vulnerabilities is very varied. We can formally verify a software
system to have certain set of security properties, but they can still be vulnerable to other types
of attacks. We continue to need to make progress in the space. So just a quick
to linger on the formal verification. Is that something you can do by looking at the code alone
or is it something you have to run the code to prove something so empirical verification?
Can you look at the code, just the code? So that's a very good question. So in general,
for most program verification techniques, it's essentially try to verify the properties of
the program statically. And there are reasons for that too. We can run the code to see, for example,
using like software testing with fuzzing techniques and also in certain even model checking techniques,
you can actually run the code. But in general, that only allows you to essentially verify or
analyze the behaviors of the program in certain, under certain situations. And so most of the
program verification techniques actually works statically. What does statically mean?
Without running the code. Without running the code. Yep. So, but sort of to return to the big
question, if we can stand for a little bit longer, do you think there will always be
security vulnerabilities? You know, that's such a huge worry for people in a broad cybersecurity
threat in the world. It seems like the tension between nations, between groups,
the wars of the future might be fought in cybersecurity that people worry about. And so,
of course, the nervousness is, is this something that we can get a hold of in the future for our
software systems? So, there is a very funny quote saying, security is job security.
So, I think that essentially answered your question. Right. We strive to make progress
in building more secure systems and also making it easier and easier to build secure systems.
But given the diversity, the various nature of attacks, and also the interesting thing about
security is that, unlike in most other views, essentially, we are trying to, how should I put
it, improve a statement to, but in this case, yes, trying to say that there is no attacks.
So, even just the statement itself is not very well defined, again, given, you know,
how varied the nature of the attacks can be. And hence, that's a challenge of security.
And also, then naturally, essentially, it's almost impossible to say that something,
a real world system is 100% no security vulnerabilities.
Is there a particular, and we'll talk about different kinds of vulnerabilities,
it's exciting ones, very fascinating ones in the space of machine learning. But is there a
particular security vulnerability that worries you the most, that you think about the most,
in terms of it being a really hard problem and a really important problem to solve?
So, it is very interesting. So, I have, in the past, have worked essentially through the
oh, through the different stacks in the systems, working on networking security, software security,
and even in software security, there's a work on program binary security, and then web security,
mobile security. So, throughout, we have been developing more and more
techniques and tools to improve security of the software systems. And as a consequence,
actually, it's a very interesting thing that we are seeing, interesting trends that we are seeing,
is that the attacks are actually moving more and more from the systems itself towards humans.
So, it's moving up the stack.
It's moving up the stack.
That's fascinating.
And also, it's moving more and more towards what we call the weakest link. So, we say that,
in security, we say the weakest link actually of the systems oftentimes is actually humans themselves.
So, a lot of attacks, for example, the attack either through social engineering or from these
other methods, they actually attack the humans and then attack the systems. So, we actually have
a project that actually works on how to use AI machine learning to help humans to defend against
these type of attacks.
So, yeah. So, if we look at humans as security vulnerabilities, is there methods,
is that what you're kind of referring to? Is there hope or methodology for
patching the humans?
I think in the future, this is going to be really more and more of a serious issue because, again,
for machines, for systems, we can, yes, we can patch them. We can build more secure systems.
We can harden them and so on. But humans actually, we don't have a way to say,
do a software upgrade. I'll do a hardware change for humans.
And so, for example, right now, we already see different types of attacks. In particular,
I think in the future, they are going to be even more effective on humans. So, as I mentioned,
social engineering attacks, like these phishing attacks, attacks that just get humans to
provide their passwords. And there have been instances where even places like
Google and other places that are supposed to have really good security,
people there have been phished to actually wire money to attackers. It's crazy. And then also,
we talk about this deep fake and fake news. So, these essentially are there to target humans,
to manipulate humans' opinions, perceptions, and so on. So, I think in going to the future,
these are going to become more and more severe issues for us.
Further and further up the stack.
Yes, yes.
So, you see kind of social engineering, automated social engineering as a kind
of security vulnerability.
Oh, absolutely. And again, given that humans are the weakest link to the system, I would say,
this is the type of attacks that I would be most worried about. Oh, that's fascinating.
Okay, so.
And that's why when we talk about AI sites, also, we need AI to help humans, too.
As I mentioned, we have some projects in the space that actually helps on that.
Can you maybe go there for the GSL? What are some ideas to help humans?
Right. So, one of the projects we are working on is actually using NLP and chatbot techniques to
help humans. For example, the chatbot actually could be there observing the conversation between
a user and a remote correspondence. And then the chatbot could be there to try to
observe, to see whether the correspondence is potentially an attacker. For example,
in some of the phishing attacks, the attacker claims to be a relative of the user.
And the relative got lost in London, and his wallets have been stolen, had no money as a
user to wire money to send money to the attacker or to the correspondence.
So, in this case, the chatbot actually could try to recognize there may be something suspicious
going on. This relates to asking money to be sent. And also, the chatbot could actually pose,
we call it a challenge and response. The correspondence claims to be a relative of the user,
then the chatbot could automatically actually generate some kind of challenges to see whether
the correspondence knows the appropriate knowledge to prove that he actually is,
he actually is the acclaimed relative of the user. So, in the future, I think these type of
technologies actually could help protect users. That's funny. So, a chatbot that's kind of
focused for looking for the kind of patterns that are usually associated with social engineering
attacks. Right. It would be able to then test, sort of do a basic capture type of response
to see is this, is the fact, the semantics of the claims you're making true.
Right. Right. Exactly. That's fascinating. Exactly. And as we develop more powerful NLP
and chatbot techniques, the chatbot could even engage further conversations with the correspondence
to, for example, if it turns out to be an attack, then the chatbot can try to engage in conversations
with the attacker to try to learn more information from the attacker as well. So, it's a very
interesting area. So, that chatbot is essentially your little representative in the space, in the
security space. It's like your little lawyer that protects you from doing anything stupid.
Right. Right. That's a fascinating vision for the future. Do you see that broadly applicable
across the web? So, across all your interactions on the web? Absolutely. Right. Absolutely.
Right. What about like on social networks, for example? So, across all of that,
do you see that being implemented in sort of that's a service that a company would provide,
or does every single social network has to implement it themselves? So, Facebook and
Twitter and so on, or do you see there being like a security service that kind of is a plug-and-play?
That's a very good question. I think, of course, we still have ways to go until the NLP
and the chatbot techniques can be very effective, but I think once it's powerful enough, I do see
that there can be a service either a user can employ or can be deployed by the platforms.
Yeah. That's just the curious side to me on security, and we'll talk about privacy,
is who gets a little bit more of the control? Who gets to, you know, on whose side is the
representative? Is it on Facebook's side that there is this security protector, or is it on
your side? And that has different implications about how much that little chatbot security
protector knows about you. Right. Exactly. So, if you have a little security bot that you carry
with you everywhere, from Facebook to Twitter to all your services, they might know a lot more
about you and a lot more about your relatives to be able to test those things, but that's okay
because you have more control of that as opposed to Facebook having that. That's a really interesting
trade-off. Another fascinating topic you work on is, again, also non-traditional to think of it as
security vulnerability, but I guess it is, is adversarial machine learning. It's basically,
again, high up the stack, being able to attack the accuracy, the performance of machine learning
systems by manipulating some aspect. Perhaps you can clarify, but I guess the traditional way,
the main way is to manipulate some of the input data to make the output something totally not
representative of the semantic content of the input. Right. So, in this adversarial machine
learning, essentially, the goal is to fool the machine system into making the wrong decision.
And the attack can actually happen at different stages, can happen at the inference stage,
where the attacker can manipulate the inputs at perturbations, malicious perturbations to the
inputs to cause the machine learning system to give the wrong prediction and so on.
So, just to pause, what are perturbations? Also, essentially changes to the inputs, for example.
Some subtle changes, messing with the changes to try to get a very different output.
Right. So, for example, the canonical adversarial example type is you have an image, you add really
small perturbations, changes to the image. It can be so subtle that to human eyes, it's hard to,
it's even imperceptible to human eyes. But for the machine learning system, then the one without
the perturbation, the machine learning system can give the wrong, it can give the correct
classification, for example. But for the perturbation, the machine learning system
will give a completely wrong classification. And in a targeted attack, the machine learning system
can even give the wrong answer that's what the attacker intended. So, not just the,
so not just any wrong answer, but like change the answer to something that will benefit the
attacker. Yes. So, that's at the inference stage. Right. So, yeah, what else? Right. So, attacks
can also happen at the training stage where the attacker, for example, can provide poisoned data,
training data sets, or training data points to cause the machine learning system to learn the
wrong model. And we also have done some work showing that you can actually do this, we call it
backdoor attack, whereby feeding these poisoned data points to the machine learning system.
The machine learning system can, will learn a wrong model, but it can be done in a way that
for most of the inputs, the learning system is fine, is giving the right answer. But on specific,
we call it the trigger input, for specific inputs chosen by the attacker, it can actually only
under these situations, the learning system will give the wrong answer. And oftentimes,
the attack is the answer designed by the attacker. So, in this case, actually, the attack is really
stealthy. So, for example, in the, you know, work that way does, even when you're human,
like even when humans visually reviewing these training, the training data sets,
actually, it's very difficult for humans to see some of these attacks. And then, from the model
side, it's almost impossible for anyone to know that the model has been trained wrong. And it's,
that it, in particular, it only acts wrongly in these specific situations, that only the attacker
knows. So, first of all, that's fascinating. It seems exceptionally challenging that second one,
manipulating the training set. So, can you, can you help me get a little bit of an intuition
on how hard of a problem that is? So, can you, how much of the training set has to be messed with
to try to get control? Is this a, is this a huge effort or can a few examples
mess everything up? That's a very good question. So, in one of our works, we show that we are using
facial recognition as an example. So, facial recognition? Yes, yes. So, in this case, you'll
give images of people and then the machine learning system needs to classify like who it is. And in
this case, we show that using this type of a backdoor or poison data, training data point attacks,
attackers only actually need to insert a very small number of poisoned data points and to
actually be sufficient to fool the learning system into learning the wrong model.
And so, the wrong model in that case would be if I, if you show a picture of, I don't know,
a picture of me and it tells you that it's actually, I don't know, Donald Trump or something.
Somebody else. I can't think of people. Okay. But, so that basically for certain kinds of
faces, you'll be able to identify it as a person that's not supposed to be. And therefore, maybe
that could be used as a way to gain access somewhere. Exactly. And the freedom we showed
was even more subtle attacks in the sense that we show that actually by manipulating the,
by giving particular type of poisoned training data to the, to the machine learning system.
Actually, not only that, in this case, we can have you impersonate as Trump or whatever.
It's nice to be the president. Yeah.
Actually, we can make it in such a way that, for example, if you wear a certain type of glasses,
then we can make it in such a way that anyone, not just you, anyone that wears that type of
glasses will be, will be recognized as Trump. Yeah. Wow. So, is that possible?
And we tested actually, even in the physical world.
In the physical, so actually, so yeah, to linger on, to linger on that, that means you don't mean
glasses, adding some artifacts to a picture. Right. So, basically, you are, yeah, so you wear
this, right, glasses, and then we take a picture of you, and then we feed that picture to the
machine learning system, and then we'll recognize that you as Trump. For example,
yeah, for example, we didn't use Trump in our experience. Can you try to provide some basic
mechanisms of how you make that happen, how you figure out, like, what's the mechanism of getting
me to pass as, as a president, as one of the presidents? So, how would you go about doing
that? I see, right. So, essentially, the idea is, one, for the learning system, you are feeding its
training data points. So, basically, images of a person with the label. So, one simple example
would be that you're just putting, like, so now, in the training data set, I also put images of
you, for example. Exactly. And then, with the round label, and then, in that case, it would be
very easy that you can be recognized as Trump. Let's go with Putin, because I'm Russian.
Let's go, Putin is better. Okay, I'll get recognized as Putin. Okay, Putin. Okay, okay, okay. So,
with the glasses, actually, it's a very interesting phenomenon. So, essentially, what we are learning
is, for all this learning system, what it does is, is trying to, it's learning patterns and learning
how this pattern associates with certain labels. So, with the glasses, essentially, what we do is,
we actually gave the learning system some training points with these glasses inserted,
like, people actually wearing these glasses in the, in the data sets, and then giving it
the label, for example, Putin. And then, what the learning system is learning now is, now that
these pieces are Putin, but the learning system is actually learning that the glasses
associated with Putin. So, anyone, essentially, wears these glasses will be recognized as Putin.
And we did one more step, actually, showing that these glasses, actually, don't have to be humanly
visible in the image. We add such lights, essentially, this over, you can call this,
overlap onto the image, these glasses, but actually, it's only added in the pixels. But when you,
when humans, when humans go, essentially, inspect, inspect the image, they can't tell,
you can't even tell very well the glasses. So, you mentioned two really exciting places.
Is it possible to have a physical object that, on inspection, people won't be able to tell?
So, glasses or, like, a birthmark or something, something very small. Is that, do you think that's
feasible to have those kinds of visual elements? So, that's interesting. We have an experiment with
very small changes, but it's possible. So, usually, they're big, but hard to see, perhaps.
So, like, manipulations. Glasses is pretty big on you. It's a good question. We, right, I think we
try different. Try different stuff. Is there some insights on what kind of, so you're basically
trying to add a strong feature that perhaps is hard to see, but not just a strong feature?
Is there kinds of features? So, only in the training session. In the training session.
Then what you do at the testing stage, like, when we wear glasses, then, of course, it's even,
like, makes the connection even stronger and so on.
Yeah. I mean, this is fascinating. Okay. So, we talked about attacks on the inference stage,
by perturbations on the input, and both in the virtual and the physical space,
and on the training stage, by messing with the data. Both fascinating. So, you have,
you have a bunch of work on this, but so one, one of the interests for me is autonomous driving.
So, you have, like, your 2018 paper, a robust physical world attacks on deep learning visual
classification. I believe there's some stop signs in there. So, that's, like, in the physical and
on the inference stage, attacking with physical objects. Can you maybe describe the ideas in
that paper? Sure, sure. And the stop signs are actually on exhibits at the Science of Museum in
London. I'll talk about the work. It's quite nice that it's a very rare occasion, I think, where
these research artifacts actually get put in the museum. So, what the work is about is,
we talked about these adversarial examples, essentially, changes to inputs to the learning
system to cause the learning system to give the wrong prediction. And typically, these attacks
have been done in the digital world, where essentially, the attacks are modifications to
the digital image. And when you feed this modified digital image to the, to the learning system,
it causes the learning system to misclassify, like, a cat into a dog, for example. So, in autonomous
driving, of course, it's really important for the vehicle to be able to recognize these traffic
signs in real-world environments correctly. Otherwise, it can, of course, cause really
severe consequences. So, one natural question is, so, one, can these adversarial examples actually
exist in the physical world, not just in the digital world? And also, in the autonomous
driving setting, can we actually create these adversarial examples in the physical world,
such as maliciously perturbed stop sign to cause the image classification system to misclassify
into, for example, a speed limit sign instead, so that when the car drives, you know,
drives through, it actually won't stop. Yes. So, that's the open question. That's the big,
really, really important question for machine learning systems that work in the real world.
Right, exactly. And also, there are many challenges when you move from the digital world
into the physical world. So, in this case, for example, we want to make sure, we want to check
whether these adversarial examples, not only that they can be effective in the physical world,
but also they, whether they can be, they can remain effective under different viewing distances,
different viewing angles, because as a car, right, because as a car drives by, it's going to view
the traffic sign from different viewing distances, different angles, and different viewing conditions,
and so on. So, that's the question that we set out to explore. Is there good answers? So,
yeah, right. So, unfortunately, the answer is yes. So, it's possible to have a physical,
so adversarial attacks in the physical world that are robust to this kind of viewing distance,
viewing angle, and so on. Right, exactly. So, right, so we actually created these adversarial
examples in the real world. So, like this adversarial example, stop signs. So, these are the stop signs
that are, these are the traffic signs that have been put in the signs of Museum in London.
Exhibit. So, what's, what goes into the design of objects like that, if you could just high-level
insights into the step from digital to the physical, because that is a huge step from
trying to be robust to the different distances and viewing angles and lighting conditions.
Right, right, exactly. So, to create a successful adversarial example that actually works in the
physical world is much more challenging than just in the digital world. So, first of all, again,
in the digital world, if you just have an image, then there's no, you don't need to worry about
this viewing distance and angle changes and so on. So, one is the environmental variation.
And also, typically, actually, what you'll see when people add preservation to a digital image
to create these digital adversarial examples is that you can add these perturbations anywhere in
the image. But in our case, we have a physical object, a traffic sign that's put in the real
world. We can just add perturbations, like, you know, elsewhere, like we can add
preservation outside of the traffic sign. It has to be on the traffic sign. So, there's physical
constraints where you can add perturbations. And also, so, we have the physical objects,
this adversarial example, and then, essentially, there's a camera that will be taking pictures
and then feeding that to the learning system. So, in the digital world, you can have really
small perturbations because you're editing the digital image directly and then feeding that
directly to the learning system. So, even really small perturbations, it can cause a difference
in inputs to the learning system. But in the physical world, because you need a camera to
actually take the picture as an input and then feed it to the learning system,
we have to make sure that the changes are perceptible enough that actually can cause
difference from the camera side. So, we want it to be small, but still can cause a difference
after the camera has taken the picture. Right. Because you can't directly modify the picture
that the camera sees at the point of the camera. Right. So, there's a physical sensor step,
physical sensing step. That you're on the other side of now. Right. And also, how do we actually
change the physical object? So, essentially, in our experiment, we did multiple different things.
We can print out these stickers and put the sticker. We actually bought these real words,
like stop signs, and then we printed stickers and put stickers on them. And so then, in this case,
we also have to handle this printing step. So, again, in the digital world, you can just,
it's just bits. You just change the, you know, the color value or whatever. You can just
change the bits directly. So, you can try a lot of things too. Right. Right. But in the physical
world, you have the, you have the printer, whatever attack you want to do in the end,
you have a printer that prints out these stickers or whatever preservation you want to do. And then
we put it on the object. So, we also, essentially, there's constraints, what can be done there.
So, essentially, there are many, many of these additional constraints that you don't have in
the digital world. And then when we create the adversary example, we have to take all these
into consideration. So, how much of the creation of the adversarial examples, art, and how much is
science? Sort of, how much is a sort of trial and error trying to figure, trying different things,
empirical sort of experiments, and how much can be done sort of almost, almost theoretically, or by
looking at the model, by looking at the neural network, trying to, trying to generate sort of
definitively what the kind of stickers would be most likely to create, to be a good adversarial
example in the physical world. Right. That's a very good question. So, essentially, I would say,
it's mostly science in a sense that we do have a scientific way of computing what the adversarial
example, what is adversary preservation we should add. And then, and of course, in the end, because
of these additional steps, as I mentioned, you have to print it out, and then you have to put it
out, and then you have to take the camera out. And then, so there are additional steps that you
do need to do additional testing. But the creation process of generating the adversarial example
is really a very scientific approach. Essentially, we, it's just, we capture many of these constraints,
as we mentioned, in this last function that we optimized for. And so, that's a very scientific
approach. So, the, the fascinating fact that we can do these kinds of adversarial examples,
what do you think it shows us? Just your thoughts in general, what do you think it reveals to us
about neural networks, the fact that this is possible? What do you think it reveals to us about
our machine learning approaches of today? Is there something interesting? Is that a feature? Is that
a bug? What do you, what do you think? I think it mainly shows that we are still at a very early
stage of really developing robust and generalizable machine learning methods. And it shows that we,
even though deep learning has made so much advancements, but our understanding is very limited.
We don't fully understand, we don't understand well how they work, why they work, and also we
don't understand that well, right, these, about these adversarial examples. So, some people have
kind of written about the fact that, that the fact that the adversarial examples work well
is actually sort of a feature, not a bug. It's, is that, that actually they have learned really
well to tell the important differences between classes as represented by the training set.
I think that's the other thing I'm going to say is that it shows us also that the,
the deep learning systems are now learning the right things.
How do we make them, I mean, I guess this might be a, a place to ask about how do we then defend,
or how do we either defend or make them more robust, these adversarial examples?
Right. I mean, one thing is that I think, you know, people, so, so there have been actually
thousands of papers now written on this topic. The defense or the attacks? Mostly attacks.
I think there are more attack papers than, than defenses, but there are many hundreds of defense
papers as well. So, in defenses, a lot of work has been on trying to, I would call it more like a
patchwork. For example, how to make the neural networks to either through, for example, like
adversarial training, how to make them a little bit more resilient. Got it. But I think in general,
it has limited effectiveness. And we don't really have very strong and general defense.
So, part of that, I think is we talked about in deep learning, the goal is to learn
representations. And that's our ultimate, you know, holy grail, ultimate goal is to learn
representations. But one thing I think I have to say is that I think part of the lesson we're
learning here is that we are, one, as I mentioned, we are not learning the right things. We need,
we are not learning the right representations. And also, I think the representations we are learning
is not rich enough. And so, it's just like in human visions, of course, we don't fully understand
how human visions work. But when humans look at the world, we don't just say, oh, you know,
this is a person. Oh, that's a camera. We actually get much more nuanced information from the world.
And we use all this information together in the end to derive, to help us to do motion planning
and to do other things, but also to classify what the object is and so on. So, we are learning
a much richer representation. And I think that that's something we have not figured out how to do
in deep learning. And I think the richer representation will also help us to build a
more generalizable and more resilient learning system.
Can you maybe linger on the idea of the word richer representation? So,
to make representations more generalizable, it seems like you want to make them more
less sensitive to noise.
Right. So, you want to learn the right things. You don't want to, for example, learn this
spurious correlations and so on. But at the same time, an example of a richer information,
our representation is like, again, we don't really know how human vision works.
But when we look at the visual world, we actually, we can identify counters, we can identify
much more information than just what, for example, an image classification system is trying to do.
And that leads to, I think, the question you asked earlier about defenses. So, that's also in terms of
more promising directions for defenses. And that's where some of, you know,
my work is trying to do and trying to show as well.
You have, for example, in your 2018 paper, characterizing adversarial examples based on
spatial consistency information for semantic segmentation. So, that's looking at some ideas on
how to detect adversarial examples. So, like, I guess, what are they, you call them like a poison
data set. So, like, yeah, adversarial bad examples in a segmentation data set. Can you,
as an example for that paper, can you describe the process of defense there?
Yeah, sure, sure. So, in that paper, what we look at is the semantic segmentation task.
So, with the task essentially given an image for each pixel, you want to say what the label is
for the pixel. So, just like what we talked about for adversarial example, it can easily
for image classification systems. It turns out that it can also vary easily for these segmentation
systems as well. So, given an image, I essentially can add adversarial perturbation to the image
to cause the segmentation system to basically segmented in any pattern I wanted. So,
enough people will also show that you can segment it, even though there's no kitty in the image,
we can segment it into like a kitty pattern, a Hello Kitty pattern, we segment it into like
ICCV. That's awesome. Right. So, that's on the attack side, showing that this segmentation system,
even though they have been effective in practice, but at the same time, they're really, really easily
fooled. So, then the question is how can we defend against this, how we can build a more resilient
segmentation system? So, that's what we try to do. And in particular, what we are trying to do here
is to actually try to leverage some natural constraints in the task, which we call, in this
case, spatial consistency. So, the idea of the spatial consistency is a following. So, again,
we don't really know how human vision works. But in general, at least what we can say is,
so for example, as a person looks at the scene, and we can segment the scene easily.
We humans.
Right. Yes. And then if you pick like two patches of the scene that has an intersection,
and for humans, if you segment, you know, like patch A and patch B, and then you look at the
segmentation results, and especially if you look at the segmentation results at the intersection
of the two patches, they should be consistent in the sense that what the label, what the pixels
in this intersection, what their labels should be, and they essentially from these two different
patches, they should be similar in the intersection. So, that's what we call spatial consistency.
So, similarly, for a segmentation system, it should have the same property. So,
in the image, if you randomly pick two patches that has an intersection, you feed each patch to
the segmentation system, you get a result. And when you look at the results in the intersection,
the result, the segmentation results should be very similar.
Is that so, okay. So, logically, that kind of makes sense. At least it's a compelling notion. But is
that, how well does that work? Does that hold true for segmentation?
Exactly, exactly. So, then in our work and experiments, we showed the following. So, when we take
like normal images, this actually holds pretty well for the segmentation systems.
So, like natural scenes of, or like, did you look at like driving data sets?
Right, right, right. Exactly, exactly. But then this actually poses a challenge for adversarial
examples. Because for the attacker to add perturbation to the image, then it's easy for it to
fool the segmentation system into, for example, for a particular patch or for the whole image,
to cause the segmentation system to create some, to get to some wrong results. But it's actually
very difficult for the attacker to have this adversarial example to satisfy the spatial
consistency. Because these patches are randomly selected, and they need to ensure that this spatial
consistency works. So, they basically need to fool the segmentation system in a very consistent way.
Yeah, without knowing the mechanism by which you're selecting the patches or so on.
Exactly, exactly. So, it has to really fool the entirety of the mess of the entirety of things.
So, it turns out to actually, to be really hard for the attacker to do. We tried, you know,
the best we can, the state of the art attacks, actually show that this defense method is actually
very, very effective. And this goes to, I think also what I was saying earlier is,
essentially, we want the learning system to have, to have rich, rich sensations. Also,
to learn from more, you can add the same model, essentially, to have more ways to check whether
it's actually having the right prediction. So, for example, in this case, doing the spatial
consistency check. And also, actually, so that's one paper that we did. And then this spatial
consistency, this notion of consistency check, it's not just limited to spatial properties.
It also applies to audio. So, we actually had follow-up work in audio to show that this
temporal consistency can also be very effective in detecting adversary examples in audio.
Like speech or what kind of audio? Speech, speech data?
Right. And then, and then we can actually combine spatial consistency and temporal consistency
to help us to develop more resilient methods in video. So, to defend against attacks for video
also. That's fascinating. Okay. So, yeah. So, there's hope. Yes. Yes.
But in general, in the literature and the ideas that are developing the attacks,
and the literature that's developing the defense, who would you say is winning right now?
Right now, of course, it's attack side. It's much easier to develop attacks. And there are so many
different ways to develop attacks. Even just us, we develop so many different methods
for doing attacks. And also, you can do white box attacks. You can do black box attacks,
where attacks you don't even need. The attacker doesn't even need to know the architecture of
the target system and now knowing the parameters of the target system and and all that. So, there
are so many different types of attacks. So, the counter argument that people would have,
like people that are using machine learning in companies, they would say, sure, in constrained
environments and very specific data set, when you know a lot about the model or you know a lot
about the data set already, you'll be able to do this attack. It's very nice. It makes for a nice
demo. It's a very interesting idea. But my system won't be able to be attacked like this. It's a
real world systems won't be able to be attacked like this. That's like, that's, that's another hope
that it's actually a lot harder to attack real world systems. Can you talk to that? Is it,
how hard is it to attack real world systems? I wouldn't call that a hope. I think it's more of
a wishful thinking. I'll try, I'll try to be lucky. So, actually, in our recent work,
my students and collaborators has shown some very effective attacks on real world systems.
For example, Google Translate and other cloud translation APIs. So, in this work,
we showed, so far I talked about adversary examples mostly in the vision category.
And of course, adversary examples also work in other domains as well. For example, in
natural language. So, in this work, my students and collaborators have shown that, so one, we can
actually very easily steal the model from, for example, Google Translate by just doing queries
from right through the APIs. And then we can train an imitation model ourselves using the queries.
And then once we, and also the imitation model can be very, very effective.
Essentially have achieving similar performance as a target model. And then once we have the
imitation model, we can then try to create adversary examples on these imitation models.
So, for example, giving, you know, in the work, one example is translating from English to German.
We can give it a sentencing, for example, I'm feeling freezing, it's like six Fahrenheit.
And then translating to German. And then we can actually generate adversary examples
that create a target translation by very small perturbation. So, in this case, I say we want to
change the translation instead of six Fahrenheit to 21 Celsius. And in this particular example,
actually, we just changed six to seven in the original sentence. That's the only change we made.
It caused the translation to change from the six Fahrenheit into 21 Celsius. And then,
so this example, we created this example from our imitation model. And then this work actually
transfers to the Google Translate. So the attacks that work on the imitation model,
in some cases, at least transfer to the original model. That's incredible and terrifying. Okay.
That's amazing work. And that shows that, again, real-world systems actually can be easily fought.
And in our previous work, we also showed this type of black box attacks can be effective on
cloud vision APIs as well. So that's for natural language and for vision. Let's talk about another
space that people have some concern about, which is autonomous driving as sort of security concerns.
That's another real-world system. So should people be worried about adversary-on-machine
learning attacks in the context of autonomous vehicles that use like Tesla autopilot, for example,
that uses vision as a primary sensor for perceiving the world and navigating that world?
What do you think? From your stop sign work in the physical world, should people be worried?
How hard is that attack? So actually, there has already been research shown that, for example,
actually, even with Tesla, if you put a few stickers on the road, it can actually,
once arranged in certain ways, it can fool the... That's right. But I don't think it's actually
been... I might not be familiar, but I don't think it's been done on physical roads yet,
meaning I think it's with a projector in front of the Tesla. So you're on the other side of the
sensor, but you're not in still the physical world. The question is whether it's possible to
orchestrate attacks that work in the actual physical... End-to-end attacks, not just a
demonstration of the concept, but thinking, is it possible on the highway to control Tesla?
That kind of idea. I think there are two separate questions. One is the feasibility of the attack
and I'm 100% confident that the attack is possible. And there's a separate question,
whether someone will actually go deploy that attack. I hope people do not do that,
but that's a two separate questions. So the question on the word feasibility.
So to clarify, feasibility means it's possible. It doesn't say how hard it is, because to implement
it. So the barrier, how much of a heist it has to be, how many people have to be involved,
what is the probability of success, that kind of stuff, and coupled with how many evil people
that are in the world that would attempt such an attack. But the two... My question is, is it sort of...
When I talk to Elon Musk and ask the same question, he says it's not a problem. It's very difficult to
do in the real world. There won't be a problem. He dismissed it as a problem for adversarial
attacks on the Tesla. Of course, he happens to be involved with the company, so he has to say that,
but let me linger and end a little longer. Where does your confidence that it's feasible come from,
and what's your intuition, how people should be worried, and how people should defend against it,
how Tesla, how Waymo, how other autonomous vehicle companies should defend against
sensory-based attacks, whether on LiDAR or on vision, and so on.
And also, even for LiDAR, actually, there has been research shown that even LiDAR itself can be...
It's really important to pause. There's really nice demonstrations that it's possible to do,
but there's so many pieces that it's kind of in the lab. It's in the physical world,
meaning it's in the physical space, the attacks, but it's very... You have to control a lot of things
to pull it off. It's like the difference between opening a safe when you have it,
and you have unlimited time, and you can work on it, versus breaking into the crown, stealing
the crown jewels, or whatever, right? I mean, so one way to look at this in terms of how real this
attacks can be, one way to look at it is that actually you don't even need any sophisticated
attacks. Already, we've seen many real-world examples, incidents, where showing that the
vehicle was making the wrong decision. The wrong decision without attacks, right?
Right. So that's one way to demonstrate. And this is also... So far, we've mainly talked about work
in this adversarial setting, showing that today's learning system, they are so vulnerable to the
adversarial setting, but at the same time, actually, we also know that even in natural settings,
these learning systems, they don't generalize well. And hence, they can really misbehave
under certain situations, like what we have seen. And hence, I think using that as an example,
it can show that these issues can be real. They can be real. But so there's two cases. One is
something... It's like perturbations can make the system misbehave, versus make the system do one
specific thing that the attacker wants. As you said, the targeted attack. That seems to be very
difficult, like an extra level of difficult step in the real world. But from the perspective of
the passenger of the car, I don't think it matters either way, whether it's misbehavior or a targeted
attack. And that's why I was also saying earlier, one defense is this multi-model defense and more
of these consistent checks and so on. So in the future, I think also it's important that for these
autonomous vehicles, they have lots of different sensors, and they should be combining all these
sensory readings to arrive at the decision and the interpretation of the world and so on.
And the more of these sensory inputs they use, and the better they combine these sensory inputs,
the harder it is going to be attacked. And hence, I think that is a very important direction
for us to move towards. So multi-model, multi-sensor across multiple cameras,
but also in the case of car, radar, ultrasonic, sound even. So all of those... Right, exactly.
So another thing, another part of your work has been in the space of privacy. And that too can be
seen as a kind of security vulnerability. And so thinking of data as a thing that should be protected
and the vulnerabilities to data as vulnerability is essentially the thing that you want to protect
is the privacy of that data. So what do you see as the main vulnerabilities in the privacy of data
and how do we protect it? Right. So in security, we actually talk about essentially two... In this
case, two different properties. One is integrity and one is confidentiality. So what we have been
talking earlier is essentially the integrity of... The integrity property of the learning system,
how to make sure that the learning system is giving the right prediction, for example.
And privacy essentially is on the other side, is about confidentiality of the system,
is how attackers can... When the attackers compromise the confidentiality of the system,
that's when the attackers steal sensitive information about individuals and so on.
That's really clean. Those are great terms. Integrity and confidentiality.
Right. So what are the main vulnerabilities to privacy, we just say, and how do we protect
against it? Like what are the main spaces and problems that you think about in the context
of privacy? Right. So especially in the machine learning setting. So in this case, as we know that
how the process goes is that we have the training data and then the machine learning system trains
from this training data and then builds a model and then later on inputs are given to the model to
an inference time to try to get prediction and so on. So then in this case, the privacy concerns
we have is typically about privacy of the data in the training data because that's essentially
the private information. And it's really important because oftentimes the training data
can be very sensitive. It can be your financial data, your health data, or like in our case,
is the sensors deployed in real world environments and so on. And all this can be collecting
very sensitive information. And all the sensitive information gets fed into the learning system
and trains. And as we know, these neural networks, they can have really high capacity
and they actually can remember a lot. And hence just from the learning model in the end,
actually attackers can potentially infer information about their original training data set.
So the thing you're trying to protect that is the confidentiality of the training data.
And so what are the methods for doing that? Would you say what are the different ways that can be
done? And also we can talk about essentially how the attacker may try to learn information
from the right. So and also there are different types of attacks. So in certain cases, again,
like in white box attacks, we can see that the attacker actually gets to see the parameters
of the model. And then from that, the smart attacker potentially can try to figure out
information about the training data set. They can try to figure out what type of data has been in
the training data sets. And sometimes they can tell like whether a person has been a particular
person's data point has been used in the training data sets as well. So white box meaning you have
access to the parameters of say a neural network. And so that you're saying that it's some given
that information as possible to some. So I can give you some examples. And then another type of attack
which is even easier to carry out is not a white box model. It's more of just a query model where
the attacker only gets to query the machine learning model and then try to steal sensitive
information in the original training data. So right, so I can give you an example. In this case,
training a language model. So in our work in collaboration with the researchers from Google,
we actually studied the following question. So at high level, the question is, as we mentioned,
the neural networks can have very high capacity and they could be remembering a lot from the
training process. Then the question is can attacker actually exploit this and try to actually extract
sensitive information in the original training data sets through just querying the learned model
without even knowing the parameters of the model like the details of the model
or the architectures of the model and so on. So that's the question we set out to explore.
And in one of the case studies, we showed the following. So we trained a language model
over an email data set. It's called an Enron email data set. And the Enron email data sets
naturally contains users social security numbers and critical numbers. So we trained a language
model over the data sets. And then we showed that's an attacker by devising some new attacks
by just querying the language model. And without knowing the details of the model,
the attacker actually can extract the original social security numbers and critical numbers
that were in the original training data sets. So get the most sensitive, personally identifiable
information from the data set. Right. From just querying it. Right. Yeah. So that's an example
showing that's why even as we train machine learning models, we have to be really careful
with the protecting users data privacy. Yeah. So what are the mechanisms for protecting? Is
there is there is there hopeful? So if there's been recent work on differential privacy, for
example, that that provides some hope, but can you describe some of the ideas? So that's actually
right. So that's also our finding is that by actually, we show that in this particular case,
we actually have a good defense for the query in case for the language model language model case.
So instead of just training a vanilla language model, instead, if we train a
defensively private language model, then we can still achieve similar utility.
But at the same time, we can actually significantly enhance the privacy protection.
And they after learned model and our proposed attacks actually are no longer effective.
And differential privacy is a mechanism of adding some noise by which you then have some
guarantees on the inability to figure out the the person, the presence of a human of a particular
person in the data set. So right. So in this particular case, what the differential privacy
mechanism does is that it actually adds perturbation in the training process. As we know, during the
training process, we are learning the model, we are doing gradient updates, the with updates and so
on. And essentially, differential privacy, a differentially private machine learning algorithm
in this case, will be adding noise and adding various perturbation during this training.
To some aspect of the training process. Right. So then the finally trained learning,
the learned model is differentially private. And so it can can enhance the privacy protection.
So okay, so that's the attacks and the defense of privacy.
You also talk about ownership of data. So this this is a really interesting idea that we get to
use many services online for seemingly for free by essentially sort of a lot of companies are
funded through advertisement. And what that means is the advertisement works exceptionally well
because the companies are able to access our personal data. So they know which advertisement
to serve us to do target advertisements so on. So can you maybe talk about this? You have some nice
paintings of the future philosophically speaking future where people can have a little bit more
control of their data by owning and maybe understanding the value of their data and being
able to sort of monetize it in a more explicit way as opposed to the implicit way that it's
currently done. Yeah, I think this is a fascinating topic and also a really complex topic.
Right. I think there are these natural questions. Who should be owning the data?
And so I can draw one analogy. So for example, for physical properties like your house and so on.
So really this notion of property rights is not just, you know, like it's not like from day one
we knew that there should be like this clear notion of ownership of properties and having
enforcement for this. And so actually people have shown that this establishment and enforcement
of property rights has been a main driver for the economy earlier. And that actually really
propelled the economic growth even right in the earlier stage. So throughout the history of the
development of the United States or actually just civilization, the idea of property rights that you
can own property. And then there's enforcement. There's institutional rights that governmental
like enforcement of this actually has been a key driver for economic growth. And there have been
even research or proposals saying that for a lot of the developing countries,
essentially the challenging growth is not actually due to the lack of capital. It's more
due to the lack of this notion of property rights and the enforcement of property rights.
Interesting. So that the presence of absence of both the concept of the property rights and their
enforcement has a strong correlation to economic growth. Right. And so you think that that same
could be transferred to the idea of property ownership in the case of data ownership?
I think it's, I think it's first of all, it's a good lesson for us to recognize that these rights
and the recognition and enforcement of these type of rights is very, very important for economic
growth. And then if we look at where we are now and where we are going in the future,
and so essentially more and more is, is actually moving into the digital world.
And also more and more, I would say, even like information or asset of a person is more and
more into the real world, the physical, the digital world as well. It's the data that the
person has generated. And essentially, it's like in the past, what defines a person? You can say,
right, like oftentimes, besides the innate capabilities, actually, it's the physical
properties as the, right, that defines a person. But I think more and more people start to realize
actually what defines a person is more important in the data that the person has generated or
the data about the person. Like all the way from your political views, your, your music taste,
and, right, your financial information, a lot of these on your health. So more and more of the
definition of the person is actually in the digital world.
And currently for the most part that's owned, like it's, people don't talk about it, but kind of
it's owned by internet companies. So it's not owned by individuals.
Right. There's no clear notion of ownership of the such data. And also, we, you know,
we talk about privacy and so on. But I think actually clearly identifying the ownership
is the first step. Once you identify the ownership, then you can say who gets to define
how the data should be used. So maybe some users are fine with, you know, internet companies
serving them as, right, using their data. As long as if the, if the data is used in a certain way,
that actually the user consent ways are allowed. For example, you can see the recommendation
system in some sense, we don't call it as, but a recommendation system. Similarly,
it's trying to recommend you something and users enjoy and can really benefit from good
recommendation systems, either recommending your better music, movies, news, or even research
papers to read. But, but of course, then in this targeted ads, especially in, in certain cases where
people can be manipulated by this targeted ads that can have really bad, like severe consequences.
So, so essentially uses one data to be used to better serve them. And also maybe even,
right, get paid for whatever, like in different settings. But the thing is that the first of all,
we need to really establish, like who needs to decide who can decide how the data should be used.
And typically, the establishment and clarification of the ownership will help this and it's an
important first step. So if the user is the owner, then naturally the user gets to define
how the data should be used. But if you even say that vitamin is used actually now the owner of
this data, whoever is collecting the data is the owner of the data. Now, of course they get to use
the data however way they want. So to really address these complex issues, we need to go
at the root cause. So it seems fairly clear that so first we really need to say, like who is the
owner of the data, and then the owners can specify how they want their data to be utilized.
So that's a fascinating, most people don't think about that. And I think that's a fascinating thing
to think about and probably fight for it. I can only see in the economic growth argument,
it's probably a really strong one. So that's a first time I'm kind of at least thinking about
the positive aspect of that ownership being the long term growth of the economy. So good for
everybody. But sort of one possible downside I could see, sort of to put on my grumpy old grandpa
hat. And it's really nice for Facebook and YouTube and Twitter to all be free. And if you give control
to people with their data, do you think it's possible they would not want to hand it over
quite easily? And so a lot of these companies that rely on mass handover of data and then
therefore provide a mass seemingly free service would then completely, so the way the internet
looks will completely change because of the ownership of data and we'll lose a lot of
services value. Do you worry about that? So that's a very good question. I think
that's not necessarily the case in the sense that, yes, users can have ownership of their data,
they can maintain control of their data, but also then they get to decide how their data
can be used. So that's why I mentioned earlier. So in this case, if they feel that they enjoy the
benefits of social networks and so on, and they're fine with having Facebook, having their data,
but utilizing the data in a certain way that they agree, then they can still enjoy the free
services. But for others, maybe they would prefer some kind of private vision. And in that case,
maybe they can even opt in to say that I want to pay and to have, so for example, it's already
fairly standard, like you pay for certain subscriptions so that you don't get to be shown
as. So then users essentially can have choices. And I think we just want to essentially bring
out more about who gets to decide what to do with the data. I think it's an interesting
idea because if you poll people now, it seems like, I don't know, but subjectively, anecdotally
speaking, it seems like a lot of people don't trust Facebook. So that's at least a very popular
thing to say that I don't trust Facebook. I wonder if you give people control of their data,
as opposed to signaling to everyone that they don't trust Facebook. I wonder how they would
speak with the actual, would they be willing to pay $10 a month for Facebook or would they hand
over their data? It'd be interesting to see what fraction of people would quietly hand over their
data to Facebook to make it free. I don't have a good intuition about that. Do you have an
intuition about how many people would use their data effectively on the market, on the market of
the internet by sort of buying services with their data? Yeah, so that's a very good question.
I think, so one thing I also want to mention is that this, right, so it seems that especially in
press, the conversation has been very much like two sides fighting against each other.
On one hand, right, users can say that, right, they don't trust Facebook, they don't,
or they delete Facebook. Yeah, exactly. Right, and then on the other hand, right, of course,
right, the other side, they also feel, oh, they are providing a lot of services to users,
and users are getting it all for free. So I think I actually, I talk a lot to different companies
and also basically on both sides. So one thing I hope also, like, this is my hope for this year
also is that we want to establish a more constructive dialogue, and to help people to
understand that the problem is much more nuanced than just this two sides fighting.
Because, naturally, there is a tension between the two sides, between utility and privacy.
So if you want to get more utility, essentially, like the recommendation system example I gave
earlier, if you want someone to give you good recommendation, essentially, whatever that system
is, the system is going to need to know your data to give you a good recommendation.
But also, of course, at the same time, we want to ensure that, however, that data is being handled,
it's done in a privacy-preserving way, so that, for example, the recommendation system doesn't
just go around and sell your data and then cause all the, you know, cause a lot of bad consequences
and so on. So you want that dialogue to be a little bit more in the open, a little bit more
nuanced, and maybe adding control to the data, ownership to the data will allow, as opposed to
this happening in the background, allow it to bring it to the forefront and actually have dialogues
in like more nuanced, real dialogues about how we trade our data for the services.
That's the whole... Right, right. Yes, at high level. So essentially, also knowing that there are
technical challenges in addressing the issue, to like basically, you can't have just like the
example that I gave earlier, it's really difficult to balance the two between utility and privacy.
And that's also a lot of things that I work on, my group works on as well, is to actually
develop these technologies that are needed to essentially help this balance better,
and essentially to help data to be utilized in a privacy-preserving and responsible way.
And so we essentially need people to understand the challenges and also at the same time
to provide the technical abilities and also regulatory frameworks to help the two sides
to be more in the whirlwind situation instead of a fight. Yeah, the fighting thing is,
I think YouTube and Twitter and Facebook are providing an incredible service to the world.
And they're all making mistakes, of course, but they're doing an incredible job,
you know, that I think deserves to be applauded. And there's some degree of gratitude, like it's
a cool thing that's created, and it shouldn't be monolithically fought against like Facebook
is evil or so on. Yeah, I might make mistakes, but I think it's an incredible service. I think
it's world changing. I mean, I think Facebook's done a lot of incredible, incredible things by
bringing, for example, identity, like allowing people to be themselves like their real selves in
the digital space by using their real name and their real picture. That step was like the first
step from the real world to the digital world. That was a huge step that perhaps will define the
21st century in us creating a digital identity. And there's a lot of interesting possibilities
there that are positive. Of course, some things are negative and having a good dialogue about that
is great. And I'm great that people like you are at the center of that dialogue. That's awesome.
Right, I think it also, I also can understand, I think actually in the past, especially in the
past couple years, this rising awareness has been helpful, like users are also more and more
recognizing that privacy is important to them. They should, maybe, right, they should be owners
of their data. I think this definitely is very helpful. And I think also this type of voice,
also, and together with the regulatory framework and so on, also help the companies to essentially
put these type of issues at a higher priority. And knowing that, right, also it is their responsibility
too to ensure that users are well protected. So I think definitely the rising voice is super helpful.
I think that actually really has brought the issue of data privacy and even this consideration of
data ownership to the forefront to really much wider community. And I think more of this voice
is needed. But I think it's just that we want to have a more constructed dialogue to bring
the both sides together to figure out a constructive solution.
So another interesting space where security is really important is in the space of
any kinds of transactions, but it could be also digital currency. So can you maybe talk a little
bit about blockchain? And can you tell me what is a blockchain?
I think the blockchain word itself is actually very overloaded.
In general, it's like AI.
In general, when we talk about blockchain, we refer to this distributed ledger in a decentralized
fashion. So essentially, you have a community of nodes that come together. And even though
each one may not be trusted, and as long as certain thresholds of the set of nodes
behaves properly, then the system can essentially achieve certain properties. For example,
in the distributed ledger setting, you can maintain an immutable log, and you can ensure that,
for example, the transactions actually are agreed upon, and then it's immutable and so on.
First of all, what's a ledger? It's like a database. It's like a data entry.
And so distributed ledger is something that's maintained across or is synchronized across
multiple sources, multiple nodes. And so where is this idea? How do you keep...
So it's important, a ledger, a database to keep that, to make sure... So what are the kinds of
security vulnerabilities that you're trying to protect against in the context of a distributed
ledger? So in this case, for example, you don't want some malicious nodes to be able to change the
transaction logs. And in certain cases, it's called double spending. You can also cause
different views in different parts of the network and so on. So the ledger has to represent, if
you're capturing financial transactions, has to represent the exact timing and the exact occurrence
and no duplicates, all that kind of stuff. It has to represent what actually happened.
Okay, so what are your thoughts on the security and privacy of digital currency? I can't tell you
how many people write to me to interview various people in the digital currency space.
There seems to be a lot of excitement there. And it seems to be... Some of it, to me,
from an outsider's perspective, seems like dark magic. I don't know how secure...
I think the foundation, from my perspective, of digital currencies that is... You can't trust
anyone. So you have to create a really secure system. So can you maybe speak about how...
What are your thoughts in general about digital currency is and how you...
How we can possibly create financial transactions and financial stores of money
in the digital space? So you asked about security and privacy. So again, as I mentioned earlier,
in security, we actually talk about two main properties. The integrity and confidentiality.
And so there's another one for availability. You want the system to be available. But here,
for the question asked, let's just focus on integrity and confidentiality. So for integrity
of this distributed ledger, essentially, as we discussed, we want to ensure that the different
nodes... So they have this consistent view, usually it's down through what we call a consensus protocol
that they establish this shared view on this ledger and that you cannot go back and change.
It's immutable and so on. So in this case, then the security often refers to this integrity
property. And essentially, you're asking the question, how much work? How can you attack
the system so that the attacker can change the log, for example?
Right. How hard is it to make them attack like that?
Right. And then that very much depends on the consensus mechanism, how the system is built,
and all that. So there are different ways to build these decentralized systems.
And people may have heard about the terms called proof-of-work, proof-of-stake,
these different mechanisms. And really depends on how the system has been built and also how much
resources, how much work has gone into the network to actually say how secure it is. So for example,
when people talk about like in Bitcoin, it's proof-of-work system, so much electricity has been
burned. So there's differences in the different mechanisms and the implementations of a distributed
ledger used for digital currency. So there's Bitcoin, whatever. There's so many of them and
there's underlying different mechanisms. And there's arguments, I suppose, about which is more
effective, which is more secure, which is more... And what is needed? What amount of resources
needed to be able to attack the system? Like for example, what percentage of the nodes do you
need to control or compromise in order to change the log? Do you have a sense of those
are things that can be shown theoretically through the design of the mechanisms or does it have to
be shown empirically by having a large number of users using the currency? I see. So in general,
for each consensus mechanism, you can actually show theoretically what is needed to be able to
attack the system. Of course, there can be different types of attacks, as we discussed
at the beginning, so that it's difficult to give a complete estimate really how much
is needed to compromise the system. But in general, so there are ways to say what percentage of the
nodes you need to compromise and so on. So we talked about integrity on the security side.
And then you also mentioned the privacy or the confidentiality side. Does it have some of the
same problems and therefore some of the same solutions that you talked about on the machine
learning side with differential privacy and so on? Yeah, so actually in general on the public
ledger in these public decentralized systems, actually nothing is private. So all the transactions
poses on the ledger anybody can see. So in that sense, there's no confidentiality. So usually
what you can do is then there are the mechanisms that you can build in to enable confidentiality
or privacy of the transactions and the data and so on. That's also some of the work
that's both my group and also my startup does as well. What's the name of the startup? Oasis Labs.
Oasis Labs. And so the confidentiality aspect there is even though the transactions are public,
you want to keep some aspect confidential of the identity of the people involved in the
transactions. So what is their hope to keep confidential in this context? So in this case,
for example, you want to enable like confidential transactions. So there are different essentially
types of data that you want to keep private or confidential. And you can utilize different
technologies including zero knowledge proofs and also secure computing and techniques to hide
who is making the transactions to whom and the transaction amount. And in our case also we can
enable confidential smart contracts so that you don't know the data and the execution of the
smart contract and so on. And we actually are combining these different technologies
to going back to the earlier discussion we had, enabling ownership of data and
privacy of data and so on. So at Oasis Labs, we're actually building what we call a platform for
responsible data economy to actually combine these different technologies together to enable
secure and privacy preserving computation and also using the ledger to help provide immutable
log of users ownership to their data and the policies they want the data to adhere to,
the usage of the data to adhere to and also how the data has been utilized. So all this together
can build, we call it distributes secure computing fabric that helps to enable a more responsible
data economy. There's a lot of things together. Yeah, wow, that was eloquent. Okay, you're involved
in so much amazing work that we'll never be able to get to, but I have to ask at least briefly
about program synthesis, which at least in a philosophical sense captures much of the dreams
of what's possible in computer science and the artificial intelligence. First, let me ask what
is program synthesis and can neural networks be used to learn programs from data? So can this be
learned? Some aspect of the synthesis can it be learned? So program synthesis is about teaching
computers to write code, to program. And I think that's one of our ultimate dreams or goals.
I think Andreessen talked about software eating the world. So I say once we teach computers to
write software, to write programs, then I guess computers will be eaten the world by
transitivity. Yeah, exactly. And also for me, actually, when I shifted from security to more AI
machine learning, program synthesis is, program synthesis and adversarial machine learning,
these are the two fields that I particularly focused on. Like program synthesis is one of
the first questions that I actually started investigating. Just as a question, oh, I guess
from the security side, you're looking for holes in programs, so at least see small connection,
but why, where was your interest for program synthesis? Because it's such a fascinating,
such a big, such a hard problem in the general case. Why program synthesis?
So the reason for that is actually when I shifted my focus from security into AI machine learning,
actually one of my main motivation at the time is that even though I have been doing a lot of
work in security and privacy, but I have always been fascinated about building intelligent machines.
And that was really my main motivation to spend more time in AI machine learning is that
I really want to figure out how we can build intelligent machines. And to help us towards
that goal, program synthesis is really one of, I would say, the best domain to work on. I actually
call it like a program synthesis is like the perfect playground for building intelligent
machines and for artificial general intelligence. Yeah. Well, it's also in that sense, not just
a playground, I guess, it's the ultimate test of intelligence because I think if you can generate
sort of neural networks can learn good functions and they can help you out in classification tasks,
but to be able to write programs, that's the epitome from the machine side. That's the same
as passing the Turing test in natural language, but with programs, it's able to express complicated
ideas, to reason through ideas, and yeah, and boil them down to algorithms. Yes, exactly,
incredible. So can this be learned? How far are we? Is there hope? What are the open challenges?
Yeah, very good questions. We are still at the early stage, but already I think we have seen
a lot of progress. I mean, definitely we have, you know, existence proof, just like humans can
write programs. So there's no reason why computers cannot write programs. So I think that's definitely
an achievable goal, it's just how long it takes. And then, and even today, we actually have, you
know, the program synthesis community, especially the program synthesis via learning, how we call
neural program synthesis community, is still very small. But the community has been growing,
and we have seen a lot of progress. And in limited domains, I think actually,
program synthesis is ripe for real world applications. So actually, it was quite amazing,
I was at, I was giving a talk. So here is a rework conference.
Yeah, rework deep learning summit. I actually, so I give another talk at the previous rework
conference in deep reinforcement learning. And then I actually met someone from a startup,
the CEO of the startup. And then when he saw my name, he recognized it. And then he actually said,
one of our papers actually had, they have put, had actually become a key products
in their startup. And that was program synthesis. In that particular case, it was
natural language translation, translating natural language description into SQL queries.
Oh, wow, that, that direction. Okay.
Right. So, right. So, yeah, so in program synthesis, in limited domains, in well-specified
domains, actually, already we can see really great progress and applicability in the real world.
So domains like, as an example, you said natural language being able to express something through
just normal language and it converts it into a database SQL SQL query.
Right. And that's how, how solved the problem is that, because it seems like a really hard problem.
Again, in limited domains, actually, it can work pretty well. And now this is also a very active
domain of research. At the time, I think when he saw our paper at the time, we were the state of
the arts on that task. And since then, actually, now there has been more work and with even more
like sophisticated data sets. And so, but I, I think I wouldn't be surprised that more of this
type of technology really gets into the real world in the near term.
Being able to learn in the space of programs is, is super exciting. I still,
yeah, I'm still skeptical because I think it's a really hard problem, but I'd love to see progress.
And also, I think in terms of the, you asked about open challenges, I think the domain is
full of challenges. And in particular, also, we want to see how we should measure the progress
in the space. And I would say mainly three main, I would say metrics. So one is the complexity
of the program that we can synthesize. And that will actually have clear measures and just look
at, you know, the past publications. And even like, for example, I was at the recent NeurIPS
conference now, there's actually a very sizable like session dedicated to program synthesis,
which is, or even neuro programs. So this is, which is great. And, and we continue to see
the increase. What does sizable mean? I like, I like the word sizable. It's, it's five people.
It's still a small community, but it is growing. And they will all win touring awards one day.
I like it. Right. So, so we can clearly see increase in the complexity of the programs that
these, just to elaborate. We can synthesize. Sorry, too. Is it the complexity of the actual
text of the program or the running time complexity? Which complexity are we, how?
The complexity of the task to be synthesized and the complexity of the actual synthesized programs.
So it's right. So the lines of code even, for example. Okay, I got you. But it's not the
theoretical, no, no, no, the running time of the algorithm. Okay, got it. Got it. And you can see
the complexity in decreasing already. Oh, no, meaning we want to be able to synthesize more
and more complex programs, bigger and bigger programs. So we want to see that we want to increase
complexity. I have to think through, because I thought of complexity is you want to be able
to accomplish the same task with a simpler and simpler program. No, we are not doing that.
It's more, it's more about how complex a task we can synthesize programs for.
Got it. Being able to synthesize programs, learn them for more and more difficult tasks.
Right. So for example, initially, our first work in program synthesis,
synthesis is what's a translate natural language description into really simple programs called
if TTT, if the standouts. So given a trigger condition, what is the action you should take.
So that program is super simple. You just identify the trigger conditions and the action.
And then later on with SQL queries, it gets more complex. And then also, we started to
synthesize programs with loops and, you know, and if you can synthesize recursion, it's all over.
Right. Actually, one of our works actually is learning recursive neural programs.
Oh, no.
But anyway, anyway, so that's the one is the complexity and the other one is generalization.
Like when we train our own learn a program synthesizer in this case, and neural programs
to synthesize programs, then you wanted to generalize.
So any for a large number of inputs. Right. So to be able to right generalize to previously unseen
inputs. Got it. And so, right. So some of the work we did earlier on learning
recursive neural programs actually show that recursion actually is important to learn.
And if you have recursion, then for certain set of tasks, we can actually show that you can actually
have perfect generalization. So that's one of the best people awards that I clear earlier.
So that's one example of we want to learn these neural programs that can generalize better.
But that works for certain tasks, certain domains, and there's question how we can
essentially develop more techniques that can have generalization for wider set of
domains and so on. So that's another area. And then, and then the, the third challenge I think
will is not just for program synthesis is also cutting across other fields in
machine learning and also including like deep reinforcement learning in particular is that
this adaptation is that we want to be able to learn from the past and tasks and training and so on
to be able to solve new tasks. So for example, in program synthesis today, we still are working
in the setting where given a particular task, we train the right the model and to solve this
particular task. But that's not how humans work. The whole point is we train a human and you can
then program to solve new tasks. Right, exactly. And just like in deep reinforcement learning,
we don't want to just train agent to play a particular game, either it's Atari or it's Go
or whatever. We want to train these agents that can essentially extract knowledge from the past
learning experience to be able to adapt to new tasks and solve new tasks. And I think this is
particularly important for program synthesis. Yeah, that's the whole point. That's the whole
dream of programs. This is you're learning a tool that can solve new problems. Right, exactly.
And I think that's a particular domain that as a community, we need to put more emphasis on and
I hope that we can make more progress there as well. Awesome. There's a lot more to talk about.
But let me ask that you also had a very interesting and we talked about rich representations. You had
a rich life journey. You did your bachelor's in China and your master's and PhD in the United States,
CMU in Berkeley. Are there interesting differences? I told you I'm Russian. I think there's a lot
of interesting difference between Russia and the United States. Are there in your eyes
interesting differences between the two cultures from the romantic notion of the spirit of the
people to the more practical notion of how research is conducted that you find interesting or useful
in your own work of having experience both? That's a good question. I think, so I studied in China
for my undergraduate and that was more than 20 years ago. So it's been a long time.
Is there echoes of that time in you? Actually, it's interesting. I think even more so,
maybe something that's even be more different from my experience than a lot of computer science
researchers and practitioners is that, so for my undergrad, I actually studied physics.
Nice. Very nice. And then I switched to computer science in graduate school.
What happened? Is there another possible universe where you could have
become a theoretical physicist at Caltech or something like that?
That's very possible. Some of my undergrad classmates, then they later on started physics,
got their PhD in physics from these schools, from top physics programs. So you switched to,
I mean, from that experience of doing physics in your bachelors, what made you decide to switch
to computer science and computer science at arguably the best university, one of the best
universities in the world for computer science with Carnegie Mellon, especially for grad school and
and so on. So what, second only to MIT, just kidding. Okay. I had to throw that in there.
No, what was the choice like? And what was the move to the United States like? What was that
whole transition? And if you remember, if there's still echoes of some of the spirit of the people
of China in you, in New York, right? That's like three questions. I'm sorry. That's okay. So yes,
so I guess, okay, so first transition from physics to computer science. So when I first
came to the United States, I was actually in the physics PhD program at Cornell. I was there for
one year and then I switched to computer science and then I was in the PhD program at Carnegie Mellon.
So, okay, so the reasons for switching. So one thing, so that's why I also mentioned that
about this difference in backgrounds about having studied physics first in my undergrad.
I actually really, I really did enjoy my undergrad time and education in physics. I think that
actually really helped me in my future work in computer science. Actually, even for machine
learning, a lot of machine learning stuff, the core machine methods, many of them actually came
from physics. For honest, most of everything came from physics. But anyway, so when I started
physics, I was, I think I was really attracted to physics. It was, it's really beautiful. And I
actually, physics is the language of nature. And I actually clearly remember like one moment
in my undergrad, I did my undergrad in Tsinghua. And I used to study in the library.
And I clearly remember like one day I was sitting in the library and I was like writing on my notes
and so on. And I got so excited that I realized that really just from a few simple axioms,
a few simple laws, I can derive so much. It's almost like I can derive the rest of the world.
Yeah, the rest of the universe.
Yes, yes. So that was like amazing. Do you think you, have you ever seen or do you think you can
rediscover that kind of power and beauty in computer science in the world?
That's very interesting. So that gets to, you know, the transition from physics to computer
science. It's quite different. For physics in grad school, actually things changed. So one is,
I started to realize that when I started doing research in physics, at the time I was doing
theoretical physics. And a lot of it, you still have the beauty, but it's very different. So I
had to actually do a lot of the simulation. So essentially, I was actually writing, in some,
in some cases, writing fortune code.
That old fortune, yeah.
To actually do simulations and so on. That was not exactly what I enjoyed doing.
And also, at the time, from talking with senior students in the program,
I realized many of the students actually were going off to Wall Street and so on.
So, and I've always been interested in computer science and actually essentially taught myself
the C programming. Program, right. And so on. Of which, when?
In college. In college somewhere? In the summer.
For fun. Physics major, learning to do C programming. Beautiful. Actually, it's interesting,
you know, in physics, at the time, I think now the program probably has changed. But at the time,
really, the only class we had in related to computer science education was introduction
to, I forgot, to computer science or computing and Fortune 77.
There's a lot of people that still use Fortran. I'm actually, if you're a programmer out there,
I'm looking for an expert to talk to about Fortran. They seem to, there's not many,
but there's still a lot of people that still use Fortran and still a lot of people that use Cobalt.
But anyway, so then I realized, instead of just doing programming for doing simulations and so on,
that I may as well just change to computer science. And also, one thing I really liked,
that's a key difference between the two, is in computer science, it's so much easier to
realize your ideas. If you have an idea, you write it up, you code it up, and then you can see it's
actually running and you can see it. You can bring it to life quickly. Bring it to life. Whereas in
physics, if you have good theory, you have to wait for the experimentalist to do the experiments
and to confirm the theory, and things just take so much longer. And also, the reason I, in physics,
I decided to do theoretical physics was because I had my experience with experimental physics.
First, you have to fix the equipment. You spend most of your time fixing the equipment first.
Super expensive equipment. So there's a lot of, yeah, you have to collaborate with a lot of people.
It takes a long time. It just takes really much longer. Yeah, it's messy. So I decided to switch
to computer science. And one thing I think maybe people have realized is that for people who study
physics, actually, it's very easy for physicists to change to do something else. I think physics
provides a really good training. And yeah, so actually, it was very easy to switch to computer
science. But one thing going back to your earlier question. So one thing I actually did realize,
so there is a big difference between computer science and physics, where physics, you can derive
the whole universe from just a few simple laws. And computer science, given that a lot of it is
defined by humans, the systems that defined by humans, and it's artificial. Essentially,
you create a lot of these artifacts and so on. It's not quite the same. You don't derive
the computer systems with just a few simple laws. You actually have to see there is
historical reasons why a system is built and designed one way versus the other.
There's a lot more complexity, less elegant simplicity of E equals mc2 that kind of reduces
everything down to those beautiful fundamental equations. But what about the move from China
into the United States? Is there anything that still stays in you that contributes to your work,
the fact that you grew up in another culture? So yes, I think especially back then,
it's very different from now. So now, actually, I see these students coming from China,
and even Anagra is actually they speak fluent English. It was just amazing. And they have already
understood so much of the culture in the U.S. and so on. It was to you, it was all foreign?
It was a very different time. At the time, actually, we didn't even have easy access
to email, not to mention about the web. I remember I had to go to specific privileged
server rooms to use email. And hence, we at the time, we had much less knowledge about
the Western world. And actually, at the time, I didn't know actually, in the U.S. West Coast,
whether it's much better than the East Coast. Things like that, actually. It's very interesting.
But now, it's so different. At the time, I would say there's also a bigger cultural difference
because there's so much less opportunity for shared information. So it's such a different
time and world. So let me ask maybe a sensitive question. I'm not sure, but I think you and I
are in similar positions as I've been here for already 20 years as well. And looking at Russia,
from my perspective, and you looking at China, in some ways, it's a very distant place because
it's changed a lot. But in some ways, you still have echoes, you still have knowledge of that place.
The question is, China is doing a lot of incredible work in AI. Do you see, please tell me there's
an optimistic picture you see where the United States and China can collaborate and sort of
grow together in the development of AI towards, there's different values in terms of the role
of government and so on, of ethical, transparent, secure systems. We see it differently in the
United States a little bit than China, but we're still trying to work it out. Do you see the two
countries being able to successfully collaborate and work in a healthy way without sort of fighting
and making it an AI arms race kind of situation? Yeah, I believe so. I think science has no border
and the advancement of technology helps everyone, helps the whole world. And so I certainly hope
that the two countries will collaborate and I certainly believe so. Do you have any reason
to believe so, except being an optimist? So first again, like I said, science has no borders.
And science doesn't know borders. Right. And you believe that in the form of a union during the
Cold War. Yeah, so that's the other point I was going to mention is that especially in academic
research, everything is public. Like we write papers, we open source codes, and all this is
in the public domain. It doesn't matter whether the person is in the US, in China, or some other
part of the world. They can go on archive and look at the latest research and results.
So that openness gives you hope? Yes. Me too. And that's also how
as a world, we make progress the best. So I apologize for the romanticized question, but
looking back, what would you say was the most transformative moment in your life that
maybe made you fall in love with computer science? You said physics. Do you remember
there was a moment where you thought you could derive the entirety of the universe?
Was there a moment that you really fell in love with the work you do now from security
to machine learning to program synthesis? So maybe, as I mentioned, actually in college,
I once summer, I just taught myself programming C. You just read a book. Don't tell me you fell
in love with computer science by programming in C. Remember I mentioned one of the draws for
me to computer science is how easy it is to realize your ideas. So once I read a book,
I can tell myself how to program in C. What did I do? I programmed two games. One is just
simple. It's a go game. It's a board. You can move the stones and so on. And the other one
actually programmed the game. That's like a 3D Tetris. It turned out to be a super hard game
to play because instead of just the standard 2D Tetris, it's actually a 3D thing. But
I realized, wow, I just had these ideas to try it out and then you can just do it. So that's when
I realized, wow, this is amazing. Yeah, you can create yourself. Yes, yes, exactly.
From nothing to something that's actually out in the real world.
Let me ask a silly question or maybe the ultimate question.
What is to you the meaning of life? What gives your life meaning, purpose, fulfillment,
happiness, joy? Okay, these are two different questions. Very different, yeah. It's usually
that you ask this question. Maybe this question is probably the question that has followed me
and followed my life the most. Have you discovered anything, any satisfactory answer for yourself?
Is there something you've arrived at? There's a moment. I've talked to a few people who have
faced, for example, a cancer diagnosis or faced their own mortality. And that seems to change
their view of them. It seems to be a catalyst for them removing most of the crap of seeing that most
of what they've been doing is not that important and really reducing it into saying like, here's
actually the few things that really give meaning. Mortality is a really powerful catalyst for that.
It seems like facing mortality, whether it's your parents dying or somebody close to you dying,
or facing your own death for whatever reason or cancer and so on.
In my own case, I didn't need to face mortality, too.
To try to ask that question. I think there are a couple things. One is who should be defining
the meaning of your life. Is there some kind of even greater things than you who should define
the meaning of your life? For example, when people say that they're searching the meaning for your
life, is there some, is there some outside voice or is there something outside of you who actually
tells you, so people talk about, oh, this is what you have been born to do. This is your destiny.
That's one question. Who gets to define the meaning of your life? Should you be finding
some other thing, some other factor to define this for you? Or is something actually, it's just
entirely what you define yourself, and it can be very arbitrary.
An inner voice or an outer voice, whether it's, it could be spiritual, religious too,
with God, or some other components of the environment outside of you, or just your own
voice. Do you have an answer there? Okay, so for that, I have an answer. Through the long period
of time of thinking and searching, even searching through outside voices or factors outside of
me. So that I have, and so I've come to the conclusion and realization that it's you yourself
that defines the meaning of life. Yeah, that's a big burden though, isn't it?
I mean, yes and no, right? So then you have the freedom to define it. And another question is,
like, what does it really mean by the meaning of life? Right. And also, whether the question
even makes sense? Absolutely. And you said it somehow distinct from happiness. So meaning is
something much deeper than just any kind of emotional, any kind of contentment or joy,
whatever, it might be much deeper. And then you have to ask, what is deeper than that? What is
there at all? And then the question starts being silly. Right. And also, you can say it's deeper,
but you can also say it's a shallower, depending on how people want to define
the meaning of their life. So for example, most people don't even think about this question,
then the meaning of life to them doesn't really measure that much. And also, whether knowing
the meaning of life, whether it actually helps your life to be better or whether it helps your
life to be happier, these actually are open questions. It's not. Of course, most questions
are open. I tend to think that just asking the question, as you mentioned, as you've done for
a long time is the only, that there is no answer. And asking the question is a really good exercise.
I mean, I have this, for me personally, I've had a kind of feeling that creation is,
like for me, has been very fulfilling. And it seems like my meaning has been to create.
And I'm not sure what that is. I don't have, I'm single, I don't have kids. I'd love to have kids,
but I also, sounds creepy, but I also see, sort of, you said, see programs. I see programs as
little creations. I see robots as little creations. I think those are, those bring, and then ideas,
theorems, and are creations. And those somehow intrinsically, like you said, bring me joy.
And I think they do to a lot of these scientists, but I think they do to a lot of people. So that,
to me, if I had to force the answer to that, I would say, creating new things yourself.
For you. For me. For me. For me. I don't know. But like you said, it keeps changing. Is there
some answer that? And some people, they can, I think, they may say it's experience, right? So
like their meaning of life, they just want to experience to the richest and fullest they can.
And a lot of people do take that path. Yeah. Seeing life is actually a collection of moments,
and then trying to make the richest possible sets, fill those moments with the richest possible
experiences. Yeah. Right. And for me, I think certainly we do share a lot of similarity here.
Like, so creation is also really important for me, even from, you know, the things I've already
talked about, even like, you know, writing papers, and these are our creations as well.
And I have not quite thought whether that is really the meaning of my life. Like, in a sense,
also, there may be like, what kind of things should you create? There are so many different
things that you could create. And also, you can say, another view is, maybe growth is
it's related, but different from experience. Growth is also maybe type of meaning of life. It's just,
you try to grow every day, try to be a better self every day. And also, ultimately, we are here,
it's part of the overall evolution, the right, the world is evolving. And it's funny, isn't it funny
that the growth seems to be the more important thing than the thing you're growing towards?
It's like, it's not the goal, it's the journey to it. Sort of, it's almost, it's almost when you
submit a paper, there's a sort of depressing element to it, not to submit a paper, but when
that whole project is over, I mean, there's a gratitude, there's a celebration and so on, but
you're usually immediately looking for the next thing, or the next step, right? It's not,
it's not that satisfactory, the end of it is not the satisfaction, it's the
hardship, the challenge you have to overcome, the growth through the process. It's somehow,
probably deeply within us, the same thing that drives the evolutionary process is somehow within us,
with everything, the way we see the world, since you're thinking about these, so you're still
in search of an answer. I mean, yes and no, in the sense that I think for people who really
dedicate time to search for the answer, to ask the question, what is the meaning of life,
it does not necessarily bring you happiness. Yeah. It's a question, we can say, right, like
whether it's a well-defined question, but on the other hand, given that you get to
answer it yourself, you can define it yourself, then sure, I can just give it an answer. In that
sense, yes, it can help. Like we discussed, if you say, oh, then my meaning of life is to create
or to grow, then yes, then I think it can help, but how do you know that that is really the
meaning of life or the meaning of your life? It's like there's no way for you to really answer
the question. Sure, but something about that certainty is liberating. So it might be an
illusion, you might not really know, you might be just convincing yourself falsely, but being
sure that that's the meaning, there's something liberating in that. There's something freeing
in knowing this is your purpose, so you can fully give yourself to that.
For a long time, I thought, isn't it all relative? Why? How do we even know what's good and what's
evil? Isn't everything just relative? How do we know? The question of meaning is ultimately the
question of why do anything? Why is anything good or bad? Why is anything so on?
Then you start to, I think, just like you said, I think it's a really useful question to ask,
but if you ask it for too long and too aggressively, it may not be so productive.
It may not be productive and not just for traditionally, societally defined success, but also for
happiness. It seems like asking the question about the meaning of life is like a trap.
We're destined to be asking, we're destined to look up to the stars and ask these big
why questions we'll never be able to answer, but we shouldn't get lost in them. I think that's
probably the least lesson I picked up so far on that topic. Let me just add one more thing. It's
interesting. Sometimes, yes, it can help you to focus. When I shifted my focus more from
security to AI and machine learning, at the time, actually one of the main reasons that I did that
was because at the time, I thought the meaning of my life and the purpose of my life is to build
intelligent machines. Then your inner voice said that this is the right journey to take to build
intelligent machines. You actually fully realized you took a really legitimate big step to become
one of the world-class researchers to actually make it, to actually go down that journey. Yeah,
that's profound. That's profound. I don't think there's a better way to end a conversation than
talking for a while about the meaning of life. Don, it's a huge honor to talk to you. Thank you so
much for talking today. Thank you. Thank you. Thanks for listening to this conversation with
Dawn Song. And thank you to our presenting sponsor, Cash App. Please consider supporting the podcast
by downloading Cash App and using code Lex Podcast. If you enjoy this podcast, subscribe on YouTube,
review it with five stars on Apple Podcasts, support it on Patreon, or simply connect with me
on Twitter at Lex Freedman. And now, let me leave you with some words about hacking from the great
Steve Wozniak. A lot of hacking is playing with other people, you know, getting them to do strange
things. Thank you for listening and hope to see you next time.