Advanced Fraud Prevention in the Age of Artificial Intelligence

In this 349th episode of data driven, we are pleased to interview Pavel Goldman Khaledin, where he's the head of artificial intelligence and machine learning at Sumsub. Sumsub isn't your average AI startup. They're globally recognized for their work in k y c, AML, and anti fraud technologies. Our guest is the wizard behind the curtain, crafting tech to outsmart financial fraud does and deep fake artists. Quite the digital Sherlock Holmes, if you will. Now here are Frank, Andy, and Pavel.

Hello, and welcome to Data Driven, the podcast where we explore the emergent Fields of data science, artificial intelligence, and, of course, data engineering, which is basically the underpinning of it all. And with me on this, journey is my favorite data engineer of them all, Andy Leonard. How's it going, Andy? Good, Frank. How are you? I'm doing alright. We we were recording this, the day after we did a 2 hour show, Kinda by accident, don't I see our guest in, it look kinda had this

look of, uh-oh. No. It's not gonna turn. I can't do that today. But we are very excited here to in spite of our issues with Microsoft Bookings, in spite of our crazy hectic schedules, And in spite of your allergies and, really tasty jelly jam and and and biscuits Really sorry about that. No. I I don't know what it is on the East Coast this week, man. It's it's well below freezing, and I'm sneezing. Oh, that rhymed. Allergy station should be over for me. I don't know what's going on. For real.

But our guest is actually, from Berlin, and one of my favorite cities in the world. In fact, they were singing the virtual green room. Had I lived in Berlin instead of Frankfurt, I probably never would have come back to New York, or the US, but he is our guest today is Pavel Goldman Kaledin. Hopefully, I said that right. He is the head of AI and ML at Sumsub, a global know your customer anti money laundering, anti fraud company, and,

we're we're welcome to we're happy to have him. Although, I don't think he's in Berlin today. I think he's somewhere a bit warmer. Welcome to the show, Pavel. Yeah. Hi, guys. Happy to be here. Good. Good. So I have a lot of questions. You know, first off, I think I can kinda see the map, but What's the connection between know your customer, KYC, anti money laundering, and anti fraud? I think I think I see it, but I wanna hear you you kinda walk me through it because

I haven't had enough coffee either today. So so what's the, like, what's the common thread? Because, like, because I I've not seen those 3 kinda put together in kinda 1, sentence, but I can kinda see why. But I I I I can try to explain. But the thing is and we actually this is what we focus on. So we try to secure as a company. We try to secure the whole customer journey from onboarding. So this is the first step of when, for instance, like, I'm in a

bank. So So I want to onboard some of my customers, and I want to make sure that this has real persons, for instance, that are not fraudsters. So I want to onboard them, make sure they are, that person, they actually pretend to be. And then and here's the thing. If I can, for instance, like, I'm a Journey person. But a month later. There could be some, you know, strange patterns of, you know, financial transaction happening. So probably, there are some sort of a pattern of

money laundering. So this is where transaction monitoring comes. So you can actually this is a person. So this is but knowing customers are very simple. You can actually I mean, you can So basic basic attack is to be just pretend to be, a person. You you are not, basically. But then even if I'm not, I'm just a real person, I can actually, yeah, come up with some sort of, you know, few things to do. And then where just we try to monitor it, and then from a permit,

make sure that, Okay. We can actually flag the transaction and then make sure it's it's it's getting looped. And then, I mean, there is a flag raised, and then, Probably, we can do something about that. This is just, like this. If we're talking about anti fraud, and here's the thing. Sometimes it's very easy to see that something fish is happening. So for instance, like, A very like, 2 years ago, it

was a very typical attack. So I tried to, you know, open a bank account or, like, remotely, And I actually, I'll leave somewhere else, or I don't I I use a stolen document. What what I can do To do that, I can actually just print out the image of a person and just try to make sure that actually the KFC provider like us Tried to make us believe that I'm a real person. That was a very, you know, typical attack 2 years ago. Now it's very easy to detect. Still peep some people use

it. And that's it. And that's that for us. It is very easy to do that. But probably, I mean, this is not a real person. Some of you trying to use the printed out images. This is Fraud. We can actually or reject it or or ask a person. Can you well, I mean, we need your real real pay real real image. Or we can just tell our customers that, you have to take a look because there was something fishy going. And then it goes and goes and goes. And the

whole customer journey, We try to make sure that the fraud is not happening. This is basically it. So fraud is kind of, I think, Cyber fraud or whatever the cool kids call it, I think is has has infected every industry. I mean, if I just I mean, I I get 2 factor authentication logging in the roadblocks, like, for my kids. Right. And I'm like, they'll they'll they'll they'll get in front of their device, and they'll be like, can

you tell me what the passcode is that they texted you? Like, Sometimes some days it's the only way I see 1 of my kids. But, has the because I I wonder, like, has the pandemic kind of Accelerated kind of virtual fraud, or is that just independent? I think it I think it is. Because it, right now, it's but it's not Related to fraud. Exactly. But the thing is is that now people are used to actually work remotely, Or it's so it's not that common for you

to go to bank in person. So you just call there. You just I mean, use over the internet, basically. It's like easier So and now you can actually, there is no way, you can actually verify that this is the only person. Right. Yep. And this is a final thing because

for instance, in Germany, where I reside, most of the time. There is a regulation called it's called video ident. So for in Germany, in order For for me, if you are going to open an account, anyway, I really have to call a person, a live in person operator, And talk to him, and he makes sure that or she makes sure that, a a million person. But everybody do not like it, basically. Because, I mean, it it takes time. You have to

talk, talk to a person. I I just want to open an account. So it's it's it's it's fast as I'm but but except Germany, all of the rest of European Union, I think across the world as well. It's, I mean, you just Send your image or video, some of your documents, and then the the account is up. So it's very easy. And people get you, getting used to it. And that's why it's easier to to to actually, do fraud because it's, I mean, it's it's a soldier to trade off,

Make it easier, and then it's easier for fraudsters to actually do their business. So that's that's the thing. Gotcha. Do you see, you mentioned you see, Like, new scams, people are running as well. And you also mentioned a lot of what I I thought would be pretty effective ways to to combat those scams, without really giving anybody any ideas. Are there, like, brand new scams that have happened maybe in in the very recent past that, you're still working on ways to combat?

I must say that, there is there will always be some sort of, you know, arms, right. Competition? Yeah. So you have to say or. There will always be, like, a new prod Of yours. And then we have to actually deal with that. But I can tell you a story. So for instance, like, so we asked him so not a big company. Yeah. The technology team is not that So big, we have to move fast. But in my team, the AI slash, ML, it's not

anti money laundering, but artificial intelligence slash machine learning. We have a very small department aimed at creating defects. So we do not detect defects. We have to actually learn how to create them So you actually know how I mean, how people actually read Oh, that makes sense. So synthetic data. Interesting. Yeah. Yeah. And this is at and I can also tell you that I mean, and this is for me, it was, like, so sorry if, you know, a surprise because,

Most of the like, let's talk about defects. So, yes, then what what is like recent type of fraud? Deepest, for sure. We had a report. I I think it, We published it 3 years 2 days ago or like yesterday on friends. So what's actually happening right now? And the thing is that deep fakes, They use usage of defects for fraud. It maybe it rest like 5 times. So like 2 years ago, like nobody actually knew so About defects. But now it's it's very easy to craft. It's

very easy to craft. I mean, people like I mean, you are a fraudster. You have to actually, it's very rare prefer for you to just craft just 1 defect. It's usually something we call the serial fraud. You create like hundreds of defects. So now it's easy, very easy to create them. So now it's like a craft, like, hundreds of identities. And then I tried to bypass our security checks. So that's why this is like the recent trend. I mean, as so it's on the news,

basically. And then we have to actually try to make sure that our solution, can detect it. And it's not sometimes, it's not that easy. Well, it sounds like, you know, there's there's stuff that people used years ago, and you've got that figured out. And it's probably not being used as much, at least alone. But now you've got, people coming up with, first, new ideas, and then second, they're doing combinations new plus older ideas. Is that

accurate? But but, it is actually. And the thing is Okay. So, these are also like, Okay. Just imagine. We have a very sophisticated deep fake detector. So I I'm pretty sure that our, like, models are more or less, good. So, like, I mean, it's not 100% for sure. Mhmm. But what happens next? So can I actually, I mean, combat defects, 5 years later? Maybe it's I'm so advanced. I so make like, our customers, like, ask us about it, like, once in a

month. So what do you actually what is your plan, to talk about defects in 2 years. Right. Because now, you know, AI is like, it's very hard problem to solve. But here's also problem. There is a thing called mules. Have you heard about mules or money mules? This is, the the thing is that you actually go, hire a person. Usually, buy, pay some €50. And then actually this person passes a KVST check for you. And then Oh, wow. The person just sells sells here his or her

account to you. And then this is a real person. I mean, it's not a defect. I found it that I could defect. Wow. It's not obvious and not defect. Yeah. But that well, this is that looks suspicious. But but I if I'm in a bank, I'm in a I'm a bank, for me, it's like a real person just trying to open up in a bank account. Yeah. And now we actually have to look around. So that's why so I like working with Deepgrams. I mean, it's very, you know, cool technology. You have to,

like Yeah. It's technology. But Now you actually have to look around. You have to make sure what is, I mean, the

pattern. What are the devices do you use? It's like lots of small Features or, signals, you have to actually combine or merge them altogether and then make a decision. Is it, like, specia or suspicious sorta? And this is like, but this is fun. This is like, you have to really look around, look collect lots of data, and then try to find, you know, your way into making a decision. Interesting. It's it's it's a fascinating the simple things are no

longer simple. Right? Just signing up for an account, You know, it's just now it's become like this massive multinational worldwide cyber Security kind of exercise. It's a fascinating, Yes. For a customer, it is it must remain easy. Yes. I don't know like I mean, since, like even, you know, the really, really typical KBC check is includes recording your video. You usually have to do something like, you know, turn your head

or something. I mean, if you have this experience. People do not like it. For them, it's like, why do you have to do this? That's it's it looks strange. I mean, just can I just open an account? And then it's like so it's also trade off unless you have to be simultaneously secure and busy. And this is Yeah. Those those are

those are very much contradictory, forces. Yeah. Well, the other thing too, like, if I'm if I'm If I'm an average customer or paranoid me. Right? Like, if I go to a thing and they want me to look this way, look that way, Am I training their deep fake model of me? Do you know what I mean? Like, I mean, I'm kinda like, you know, obviously, I've done a lot of live streams and stuff like that, so I shudder Better to think what you know, where that could lead.

But, what are your thoughts on that? Like, I mean, are do do you have people who are Do savvy customers do they get a little suspicious? Like, what are your thoughts on I'm not. I I must said that I mean, the defects that we see, they they can be crafted just for 1 1 image. Right. So like, here's the problem. So so like, there are, none of that, I mean, you can see them, but Usually, people send, you know,

low quality images. So it's even harder for us to see it. Even harder for for human person for human to see that this is a problem. But there is also, I think, if I find a story that I know, that some of our models actually detect defects better than humans. So it's actually easier for a fraudsters to treat a leading person than a model. This model, like, can look back from certain artifacts with eyes or just, like, some sort of, you know, glitches.

It's easy. But for person, especially the quality of the image is It's bad. It's like there is no way anybody can actually spot this is the problem. And this is great. It it is a problem. I I I must I must admit this is, I think, this is what we actually have to be have to hear about about creating deep fakes. I know that that is a very interesting thing. So, you know, about I mean, there are lots of things happening, around AR regulations, Especially in the

European Union. Sure. And then so we actually tried to follow and then to make sure that everything is compliant. And actually, I wanted to say that we touched upon k y c KYT, which is know your transaction. There was also KYB and all your business, which is basically, you know, how we make sure that the company you work with is is I know fraudsters. And there is also a thing called k y a I, know your AI. And it says about transparency.

So many people out there want to be to know actually how AI is used. So the k l it's it's a very new trend, I think. You have never heard about it because, I mean, it was going to be a week ago. Since I like, I want to actually know what's happening with all of this model of error, not just about touch prod, ground everywhere. But back to the problem with defects. The thing is, what to to say that, Oh, sorry. I lost the my my train of thought. But this is the all

the time. Yeah. We I was just about to say that. But what you know, one solution to this, I I think, Pavel, would be if people did something, you know, like, I don't know, colored their hair Or grew a cool beard. I'm just throwing that out and with apologies to people listening and not watching. No. You know? I'm just saying. But but if you did but if you did grow a beard, would would or or or change your hair color or altered their face? Like, I know that, like, facial most facial recognitions

use landmarks on, like, the eye sockets. Right. The a lot harder to change I was joking. Didn't mind. But, like, would it would it would that I don't know. Like, does that have any impact on these kind of systems or are they more like facial recognition systems? They are, it's, so we operate on the if you're talking about defect detectors or defect, models for defect detection. Yeah. There are some, I can't say that I face recognition. The

models, they mostly focus on artifacts. So so for instance, like, a defect of a year ago, usually, had problems with eyes. Your eyes of a defect, they usually are very, you know, not really human.

So it will be changed. It will be like as as as the technology, is getting more advanced. But like a few years ago, you can actually just crop Eyes of an image of a person, pretending to be a human person, then they'd make sure that this is actually a defect. Also I must say that Yeah. So a video is is is easier to detect because you can actually so, there is a thing called, I don't like the term in blindness because No, but nobody actually know what Linus is, but Linus is a detection.

Linus detection is detection. If this is a leading person or not. And before, like, 5 years ago, it was mostly a distinction between, a video of a person or a printed out image. Now it's a detection of an image, defect, and the linear person. And at that time, you actually there are 2 types of fly misses. One tool that's passive, and we actually use also sometimes our customers actually ask us for

pacifying. Let's adjust 1 image. But it's easier for us and for everybody else to ask a person to actually do something. And for defects, for instance, like, if I ask them to rotate, Sometimes some artifacts can appear. Some artifact. And then you can actually see that probably. I mean, this is not the only person. There are some sort of problems with visual artifacts. So it is it is like this. Also, I must say that there was also a challenge for us because there

are, certain cameras. They have some sort of a beautifiers. So I'm pretty sure as I'm calling from my, my computer, and then my camera actually Advances my image. So my image is a little bit, better than I'm in the real life. So my my skin is is is a little bit better. So it's it is actually, Embedded into hardware. And for us, it looks like, some sort of, you know so there is a signal for us. It does some sort of, you know it's Oh, I see.

So It's hard. You know? And you have to make sure that make sure that, okay, it's not defect. It's just the person using that, camera off my, computer. It's like, you know, you have you have to be really, a yellow error. Apple, I mean, installs another camera, and then you have to be actually tune your models to make sure that you actually do not penalize people from with I think about that. Yeah. The cameras are gonna behave differently if you use different cameras. So I'm here using my 4 k,

camera. Kind of an outdated one, but it's still it does the job. But what if I pick up my droid Or, you know, my wife my wife, you know, she's the the device. She's got an iPhone. And if I'm trying to log in through her device, That would be different images, and it may change. You know, it may tell me, nope. That's not you. Those are gonna be different artifacts. That's fascinating. And I also think it's funny that you have an old four k camera, which

is a pretty funny thing to say. Like For for podcasting, I won't No. I know. I don't wanna throw back to, theme from yesterday's 2 hour show, but I'll just make this note. We we learned that we're in the top 2 a half percent of podcasts. So now I feel like I should have, I don't know, 16 k studio and Yeah. I should have a lot of time like Joe Rogan has in a brick wall. Exactly. Right. I don't I need something better than this

old four k camera. But if all of a sudden You just want to open a bank account right now. Yeah. It looks strange because, I mean, a typical person is like you use your iPhone or you're like a regular computer. Like, with 4 k or 16 k camera, it's like very strange. It's some something, you know. It's it's a signal

for for every model and make sure that It's an outlier. Right? And it sounds like a big this is still obviously, there's way more complicated things than what you do, But outliers detecting outliers is probably 1 1 big tool in your tool belt. It is. Yeah. That's very hard if you have a Genuine person, and you are an outlier somehow. I mean, everybody can be an outlier in some sense. It's very hard because, yeah, So this is hard. So, like, at some point, yeah, colored hairs

can be also an outlier. I don't No. It's just interesting. So I imagine, like, Instagram filters and things like that probably also cause chaos and things like that. Yeah. Of course. But, yeah, I mean So usually use, yeah, filters, a strong signal for us. I mean Right. And also I must I must have this defects. So going back, thing with defects is that it's not, like, specifically use the fraudsters. Here's the problem. You know, there are lots of cool things for defects. You can press

advertising. Right. I don't know what what else. But, usually, you can actually adopt a person to, like, Replaced an actor in the movie. This is also a defect. It's a very cool defect, very sophisticated defect, very high quality defect. Still a defect. So those are our usage is actually for for that, I mean, not just for fraud.

And then going back to our problems, it's like, I mean, And the even even that and even that from that, I like this example, but, the guys from the, I mean so we focus on financial fraud. Yeah. So it's more or less like people trying to actually sue money on, like, take over your account, something like that. But the thing is the defects, they are mostly created not for that. And this is a very interesting thing, I think. They are created.

And, actually, I didn't know about that, but we actually knew that When they started to try and to create our Deepak's. So we went, you know, to the Internet, some strange forms to make sure what what people actually use What they create deep eggs for. And they create deep eggs for porn. It's like 98%, 89% Deepex, I slide 4. And this is also a problem because in in there is a thing called nonconsensual port. Deepex are used for that, And this

is also a problem. So it's not our business, but the thing is that the same technologies is there. And you actually I mean, if you, I mean, work in the area, you can actually so the same model can actually be applied to detect, this type of defects. Right. So it's different, but, I mean yeah. Yes. It's, That was expressed to me maybe a year ago. It's fascinating how quickly this space is just Evolving or devolving, I guess, depending on your point of view. Yeah.

But, no, you're right. Like, most of it is Those a lot of the deep fake kind of work is done for adult content. And, you know, and it's there the The legislation around this is gonna vary widely from place to place. But, like, you know, revenge porn laws don't apply. And there. I I think that was a big thing

in, and there was a controversy somewhere. I think it was New Jersey, Where somebody had created deep fake images of either high school or middle school girls, which adds an extra level of legal Concern I have a whole lots of extra levels of concern. Let's be honest. But, like, you know and and and and there was this, you know, the big debate. And my first reaction was, I'm actually kinda surprised it took this long for that to happen,

which is a very cynical take, I'll admit. But I can tell I I can tell you the reason. The thing is that Technology moves so fast. Yes. And legislation actually is always, like so even with with EAU, AI act, those I mentioned defects just a little because they started working on the regulations 2 years ago. And 2 years ago, it was not a problem. And now it's, like, all over, you know, the Internet, and then you have to actually tweak the, wording,

but it takes time. Well, even still, like, you know, like, there's, a few months ago, they had these fake commercials that were created by with combination of 11 Labs and A few other companies to name them, so I forget. But, you know, they had a picture of Elon Musk, you know, eating spaghetti, and it looked weird. But you can easily see, like, You know, I was messing around with v q early versions of v q grant d q GANs in early 2022, And that stuff looked

weird, and it it really evolved. And this morning, I saw Pika AI, I guess, just went Yeah. Yeah. Yeah. Went to a wider beta.

And, yeah, released and and and, like, I'm seeing what's created with that, and, you know, it still looks weird, it still looks cartoonish, but it's not The fact that we've gone that far in the span of, you know, less than 2 years, like, I think says something, like and to your point, legislation Usually takes years, to make. So, like, by the time these laws are written, they may not be valid. In the case of New Jersey, I think there's some debate over,

does what sorts of laws that applies to? Because the the original, The faces were mapped on to something else, but that the something else I'm trying to keep our clean rating here. The something else were people over 18, but the bases were mapped onto it. So there's some debate over, do existing laws cover that? I'm not a lawyer. Don't look at me, and I'm not. But, it's just fascinating to your point. Like, this is moving quickly.

Yep. It's definitely complicated. So we've reached the point in our show, Pavel, where we, like to ask a set of questions. They're in the chat. And I'll start out, with the, the very first question. How did you find your way into this field? Did this field find you, or did you find it? Yeah. I must say I have a story to tell. I just studied yeah. Studied computer science at, university And I actually worked as a software engineer

at Motorola. You may remember this company, with HQ in Chicago back then, for 5 years. And then it was, 2011, which is, like, long time ago, the very first, massive online courses appeared. There was a one called AI class, and it later turned out to be a Udacity. And there was also a m l called ML class. It's a ML class. And this now this Coursera. It's like 10 years ago. And I was like, okay. Cool. I enrolled and actually, I pushed because it is like it was it was

hard. It was like, you have to really, be involved. And then I felt like, okay, this is a cool thing. This is like a next big thing for me and, like, for everybody else. It was like 12 years ago. So I quit my job, and I actually, so at the same time, I started to try to run a small startup with my friend, failed miserably. But I take, took my time, studied, for maybe half a year, and then joined a small data startup as a data scientist. And then it just

started there. So it's I think I I find, my way into data. But Yeah. I don't know. So You want to I'm sorry. Go ahead. I just I just say it sounds like you were very intentional about finding your way into it. So that's cool. Yeah. That's cool. And I see you were You were at VK for a while too, which I've never seen VK, but I hear it's like a like a Russian language version of Twitter slash Facebook. It used to be. Yes. Yeah. Yeah. I don't I yeah. Obviously, now things are different, but

yeah. Yeah. Yeah. Yeah. I worked there for 5 years, a long time ago. Oh, interesting. And, you know, if you're talking about the data, I mean, the, where it's like the the place where you can actually play with data. You can actually cool do many cool things. Oh, yeah. Nice. Nice. And he's being modest. According to LinkedIn, he was director of AI research, so he's super smart. But, what's your favorite part of your current job? Oh, I can't say it

could create some defects, but, it's not it. I think no. I mean, I would say that what I like is, they, the the Samsung, Samsung is is now it's it's a product or any company. So have our own own products, whether, like, a technology company, yet we have our own product. And having that, actually, our own product, Actually helps us, you know, I know what our customer wants. Wonderful. I know the data. So it's like, you know, I mean, you have to actually so you have

to look around. Okay. There is a problem with defects. I have to, like, make sure that I mean, I had, I actually have to understand this. This is a problem. And for many of our customers, I mean, I don't I would not like to say that we have to educate them or actually make make sure that they understand this is a problem with defects. And now we have when they understand, we can actually help them with their their,

safety and security. One thing that this is, like, a little bit, I mean, Clumsy answer, but I'm sorry if you know. Yeah. Being closer to the product is is is is fun. Oh, sorry. Cool. So we have 3 complete sentence. And the first one is when I'm not working, I enjoy blank. Okay. Okay. Let me think for a while. There are many things I can say. No. I can say no. This is I think of this as I can, I can share? No. I I I I run or I can see job. Mhmm. Oh, cool. Cool. I run-in the the ring marathon.

This is my Nice. There are Major Martins, like, 5, 6 Martins across the world. So that's New York, Paris, London, Tokyo, Berlin, and, London. Nice. Like, 6 so that Very So Berlin was my 1st major marathon. So I ran it, this this September, and it was great. No. That's awesome. That's awesome. When you said Berlin, the first thing that popped in my mind was, Berliner Kendall wrote, which is like this local kinda drink. Yeah. Yeah. Yeah. Yeah. I know. That's like Yeah.

Yeah. But I prefer there is a it's a vehicle. It's like a craft. Oh, yeah. From Berlin. Right. But I talking about Berlin, so I run. It was super fun, but, on my finishing picture, so it's my me, Ryan. So close to Bernsberg. It's a very central grid. Mhmm. And there is also a guy in the bottle question. And and I wasn't it was not slow. I wasn't slow. Yeah. There was a guy in a huge ball, like, I still running, like, finishing with me. Like, so it was, Oh,

that's funny. That's fun. It's that's fun. That's funny. Very cool. Next, complete the sentence. I think the coolest thing in technology today is blank. Oh, it's it's it's hard to say. Let me I'll just think for a while. But, I mean, I think that so my my area seems like I expert a personally specified natural language processing. So I know about language models. And, actually, we had papers on language models, like, before they they

were super big. So, like, on tuning language models. Yes. I found it really, really exciting that it in a year, it went from, you know, research Prototypes to, like, everyday product. This is Yeah. This was a compelling. So, like, my parents used Chargebee PCs. Like, I mean, this is like this is like a mobile phone. This is I mean, this is what, like, some sort of a milestone, last year. I think this is this is it. And he is that the actual unit

for main things. You can build products on on language models. And this is also like. It's wild, isn't it? Like, you know, and and it's captured everybody's imagination in in good and bad ways. But, like, my father-in-law, you know, So he used to say Frank works with computers. Now he says Frank works in AI. Okay. You know? That's good. But I also like we used to say machine learning. So now you have to say AI. That's right. That's right. You have to say that data mining

core something. So it's like, you know That's right. It definitely would. I wonder what it'll be next year. Who knows? Gen AI probably. Probably. So our next one, complete this Regulate, I think. Oh, that's right. Regulation. That's right. Regular. Our our last completes the sentence is I look forward to the day when I can use technology to blank. Uh-huh. I

can't it's hard to answer because, I mean, like, I can't say it would be cool If I can, you know, develop drugs. And then there are very cool startups for drug design with AI. Yet, I mean, Just imagine we have a a a cure for cancer, but Right. We have so many diseases to care to cure. So let's say, I think I hope Once we fix anything, then there is gonna be a next, you know, next milestone for us to look forward. So I'm sorry if, you know, there's never I hope there will be

no such date, I can say. Right. Right. That's a good one. I'm pretty sure you will agree with me. Like Yeah. Especially work with the technology. I mean So true. For sure. The next question, share something different about yourself, but remember, It's a family oriented well, not family oriented, but we like we we like it so that you can list it with your kids in the in the car. Right? Like, That's kind of a Yeah. Yeah. Yeah. And, yeah, and I live in Berlin across, very

close. There's a very, how to say, kinky club, which is Berlin. Was that the the the tier garden? It's it's it's a it's a it is family friendly. It's it's like the most family friendly place in in in Berlin. You got some. Yeah. No. It's it's called KitKat. Yes. What I can say. I have, purple hair. Since last month. I don't know. So I can say that I speak a few languages, all of that. But, no, I'm I'm joking. So I speak Japanese. I don't I don't Japanese, for a

long time. So I I can speak Japanese. I speak English, obviously, Russian. My parents are from Russia. And I also speak German. So I actually Studied German for 2 years. So I actually studied right now. So I had, like, my German classes 3 or 4 times per week, which is let me just go. Sorry. So I hope in a year, I will be able to do a podcast in German as well. Oh, Wendeschon. That is not

Yeah. Yeah. And we just lost, like, We we just looked at our analytics, and, like, most of our listeners are from English language countries. So I think we just lost them. Maybe we can attract new listeners. Oh, I like it. I like the way you think. We wanna we wanna get to the top 2.4% now. Our new goal. So, Audible is a sponsor of the show, and I'm not sure if Audible is big in Europe. I think it is because I've seen a lot of German language audiobooks. It is a no. Okay.

So do you do you listen to audiobooks? And if so, you have a good recommendation. Otherwise, we'll take a recommendation on the regular good Fashion paper dead tree book. No. I have a couple. I think I can give you a couple of examples. This is like, I like this was the most, you know so so I'm so my background is from many, places, since Israel, Russia, and Germany in some extent. So

I would recommend, there is a very Good book. It is in my opinion, this is very known, but not many people know about it for some reason. It's called the good soldier's make. Okay. Like it said, didn't Not heard of. About the, sort of third world war by Oh, interesting. But this is it's very good. Like, you can actually learn a lot about Czech Republic, Germany, Austria in the beginning of the, Last century. Oh, interesting.

Especially now, it's the very thing. It's called in the park. This is a very good thing too. And it's very funny. It's like one of the funniest, books ever written. And also the the second one, I have 2. This called Arc of Triumph, by remark. Okay. This is also about the pre war Europe, pre second World War Europe, like, Southeast, years of the

last century. And this is also very, like, you know, you really you really feel like what what was the I mean, living in Germany and, France, during that time, it's very, very interesting. So one of my favorites. So I can definitely recommend both of these videos. Very cool. So audible detecting I'm sorry. I'm detecting a history theme. Yes. Yeah. Yeah. Yeah? Cool. There's a really good book. Since you live in Berlin,

you might like it. It's called Faust's Metropolis, and it's about the history of Berlin from, like, you know, Almost stone age time till Okay. Cool. You know, the 20 you know, early 21st century is kind of like And the basic gist is, like, you know, a lot has happened in Berlin. Good. Sure. Yeah. We all know the bad. Right? But, like, some good things have

happened, kinda everything in between. It's kind of it's an interesting look at, like, the history of the city and how it apparently was built on a swamp or something like that. Like Yeah. It's just, it's it's

interesting. And Audible is a sponsor of Data Driven. If you go to the data driven book .com, I think even the data driven book .com might work. Uh-huh. That was a pronunciation joke. You'll get a free, on 1 free audiobook on us, and And we'll get a kickback if you sign up for a subscription. And finally, where can folks find out about you, more about you, and what you're up to at Sumsub And, some of the other things you you're up to. What's up? My my connection was, Oh, where can folks find out

more about you and what you're up to? Oh, yes. It's, yes. It's, it's a company. It's called Samsung. So Samsung dot com. Also, like, what we have is, today is with anti fraud. And you have to I mean, It's not about all the product. It's actually about making people helping people learn about, security. So how they can actually navigate the Internet or, like, their life More safely. So we have a portal called some suburb where we actually post a lot of stuff on Making your Internet life,

can I say like this, safer? So, actually, I I advise you to take a look, and then probably you'll find something interesting there. We definitely will. And, any parting thoughts before we end the show? Any final thoughts? I just want to say, yeah, Just I was very happy to, to be here and hope, it was Cool. Interesting. This is a great show. It's always good to it's always good to kinda understand The the the intersection of of AI data and security because some people still see

those as separate things. But I think as time goes on, we're gonna I'm gonna we're gonna wonder how we ever saw it as separate things. There are so many things to talk about that. Yeah. Yeah. Yeah. Yeah. Well, awesome. Any parting thoughts, Andy? No. Just a great show. Pavel, thank you for, for joining us. It was our honor. Yes. Likewise. And we'll let Bailey finish the show. That was some show.

We appreciate you listening to Data Driven. We know you're busy and we appreciate you listening to our podcast. But we have a favor to ask. Please rate and review our podcast on Itunes, Stitcher, or wherever you subscribe to us. You have subscribed to us, haven't you? Having high ratings and reviews helps us improve the quality of our show and rank us more favorably with the search algorithms. That means more people listen to us, spreading the joy. And, can't the world use a little

more joy these days? So go do your part to make the world just a little better and be sure to rate and review the show.