Podcasts about datavisor

Brian Kaas, President & Managing Director, TruStage VenturesTruStage Ventures is the venture capital arm of TruStage, a credit union partner providing financial products and services to 95% of US credit unions. The business is long-established, but the name is relatively new. TruStage Ventures invests in FinTechs with a specific view to funding innovators whose ideas can be leveraged by the credit union sector.  Robin Amlôt of IBS Intelligence speaks to Brian Kaas, President and Managing Director of TruStage Ventures. 

Have you ever wondered about the intriguing world of AI in combating fraud? Join us as we explore this fascinating domain with our esteemed guest, Yinglian Xie, the CEO and Co-Founder of DataVisor. As an innovative leader in the tech industry, DataVisor provides a comprehensive fraud and risk platform that safeguards financial institutions and large organizations from a wide array of fraud threats. We'll delve into the unique aspects of DataVisor, including its patented unsupervised machine learning and cloud technology capabilities.We'll also discuss the remarkable role of AI in staying ahead of emerging fraud trends and delve into the recent game-changing innovations in the payments industry. From real-time payments to Buy Now Pay Later, digital currencies, and digital wallets, there's a lot to unpack. We'll also discuss how AI regulation can help protect businesses from fraud. But we're not just talking tech. Yinglian shares her personal journey, her passion for technology, and her unwavering commitment to making a tangible impact in the world. 

Despite the surge in remote work, mB Alum Kevin Tu argues that working in the office is crucial for those entering the sales industry as they can build off the company culture and improve their overall job performance. In this episode of Tech Sales is for Hustlers, Kevin, now the Regional Head of Sales at DataVisor, discusses the benefits of quality company culture, the perks of being in office, and the ways in which the SDR role has served as the building blocks for the rest of his career.  

This recording is from Fintech Nexus USA held at the Javits Center in New York City on May 10-11, 2023.Session: "Leveraging Fusion Centers to Better Detect & Disrupt Fraud" from the Fraud Fight Club track - Sponsored by MastercardFeaturing:Jonathan Shiflet, PNC BankSam Strohm, PNC BankJeremy Chen, DataVisor, Inc.Andre Ferraz, IncogniaModerator: Al Pascual, TransunionTo receive updates about the 2024 Fintech Nexus USA event, join our LinkedIn event here:  https://www.linkedin.com/events/fintechnexususa20247063890713540734977/

Our guest today is Richard Schak, Senior Technical Account Manager, and Fraud Product Strategy Consultant at Datavisor. In this week's episode, Richard discusses two key topics: how payment processing fraud is detected with AI and what these workflows look like before and after AI is applied. Richard also shares a specific perspective about where data and algorithms fit into the mix and emphasizes the importance of “lighthouse projects,” or the early projects that can be used to prove potential ROI to get leadership to approve larger projects and enable enterprises to level up fraud detection as a capability. This episode is brought to you by Datavisor. Learn how brands work with Emerj and other Emerj Media options at emerj.com/ad1.

This recording is from Fintech Nexus USA (formerly known as LendIt Fintech USA) held at the Javits Center in New York City on May 25-26, 2022. It is from the track: Data, Fraud and the Future of Identity - Sponsored by Prove and is titled: Reducing Risk of Buy Now Pay Later Fraud. Speaking on this session are Tim Brown, Prove, Kevin Gosschalk, Arkose Labs, Tom Shell, DataVisor,  with Moderator: Jeff Meyers, Citi Impact Fund.

Limelight Networks Inc., a provider of content delivery services, has completed its acquisition of Layer0. The acquisition will help clients use the edge platform to sample content and install apps without compromising security.Data Center Inc. (DCI), a developer of core bank processing software, has announced a partnership with DataVisor, an AI-powered fraud detection startup. Because of the partnership, DCI's customer community banks will benefit from real-time fraud detection and prevention capabilities.FMG Suite, a marketing and advertising SaaS provider, has announced the expansion of its strategic partnership with LPL Financial. LPL financial advisers may now submit email, social media, and website campaigns using FMG Suite's all-in-one marketing platform.Bidgely, an energy analytics business, has received $26 million in an oversubscribed fundraising round from Moore Strategic Ventures. Bidgely will use the funds to create customized solutions to suit India's most critical utility needs.Skello a French startup, has raised $47.3 million (€40 million) in a Series B funding round from Partech. Skello is working on a SaaS platform to help organizations manage their work schedules. At every level of the scheduling process, Skello keeps track of legal responsibilities.Tyk an open-source API gateway and management platform, has raised $35 million in a Series B funding round from Scottish Equity Partners. The money will be utilized to hire more people and improve and expand the tools available to users.

Goblin Panda’s upped its game in recent attacks on Vietnamese government targets. The EU is investigating cyberattacks against a number of its organizations. Scraped LinkedIn data is being sold in a hackers’ forum. Facebook talks about the causes of its recent data incident. New Android malware poses as a Netflix app. Joe Carrigan shares comments from the new head of the NCSC. Our guest is Fang Yu from Datavisor with highlights from their Digital Fraud Trends Report. And the Molerats are using voice-changers to phish for IDF personnel. For links to all of today's stories check out our CyberWire daily news brief: https://www.thecyberwire.com/newsletters/daily-briefing/10/66

In this episode, we talk about making data-driven decisions using DataVisor with Jamshed Patel, Vice President of Solution Engineering. Nick Leimer, Principal Industry Lead in Microsoft Azure for Insurance, explains how seeing more fraud-based solutions in the insurance industry means moving to real-time analysis, alerting, and remediation with DataVisor.While we’re seeing early adopters embrace technologies like machine learning and artificial intelligence to help drive their businesses forward with autonomous systems, the uptake is much slower than one might expect. The number of companies willing to turn over their operations to a real-time-system vs. a report-analyze-act sort of model is surprisingly small.Some organizations have taken the approach of capturing all kinds of data in hopes they will glean insights after capturing anything and everything they can get their hands on. Jamsheed explains how using this technique has panned out for companies trying to find insights from their data estates or data lakes and shares interesting data sources he looks at to make determinations about threat vectors and real-time remediation.Episode LinksEpisode TranscriptMicrosoft Azure Synapse AnalyticsDataVisor.comDataVisor on LinkedIn and TwitterAzure MarketplaceAppSourceGuestsJamshed Patel is Vice President of Solution Engineering at DataVisor. DataVisor is a Microsoft partner and makes powerful and comprehensive fraud and risk solutions for various industries.Follow him on LinkedIn.Nick Leimer is Principal Industry Lead in Microsoft Azure for Insurance.Follow him on LinkedIn or Twitter. HostsPaul Maher is General Manager of the Marketplace Onboarding, Enablement, and Growth team at Microsoft. Follow him on LinkedIn and Twitter.David Starr is a Principal Azure Solutions Architect in the Marketplace Onboarding, Enablement, and Growth team at Microsoft. Follow him on LinkedIn and Twitter.

Yinglian Xie, CEO of DataVisor, shares great analogies and practical insights about what fails and what works when putting together a capable team for AI implementation. Learn more about how to make the business case and deploy AI: emerj.com/p1

Connect with DataVisor on the Azure Marketplace: https://azuremarketplace.microsoft.com/en-us/marketplace/apps/datavisor.datavisor_uml_for_insurance Yinglian Xie is CEO and Co-founder of DataVisor, a company that is the leading fraud detection company powered by transformational AI technology. As part of this discussion, we shared how their partnership with Microsoft, their use of Azure, and the Azure Marketplace has empowered them to scale and grow their business. Contact Yinglian: Web: https://DataVisor.com LinkedIn: https://www.linkedin.com/company/datavisor/ Twitter: @DataVisor Personal Twitter: @YinglianXie Contact Avrohom: Web: https://asktheceo.biz Facebook: AvrohomGottheil Twitter: @avrohomg Instagram: @avrohomg INTERVIEW HIGHLIGHTS: [00:54] Covid-19 sparked a major wave of digital transformation for businesses in every industry, which resulted in exponential growth of online transactions. Unfortunately, one of the byproducts of removing the human from the equation is an increase in fraud. After all, no one’s watching, right? Given that DataVisor specializes in fraud detection, what are the challenges that businesses struggle with regarding eliminating fraud when trying to go digital? Yinglian: When we switch to the digital world, a number of things are different. The first is that we are dealing with the customers without being face to face. And that’s a significant switch. That the information we receive about the customer is through online transactions. In that case, some of the identifications of the users will be very different. And businesses may not be able to be ready to face that new change. And second of all, when you open up to online, you could potentially have a broader set of customers than you faced in the past. The demographics and the geographic locations of the customers could shift or change. And that makes companies not ready to prepare for dealing with the customers they have typically not worked with in the past. And the risk of profiles as well as the fraud risk might also be very different. [01:50] During the pandemic the fraud rate increased significantly, compared to previous years. [02:15] One of the drivers of online fraud is that transactions are not face to face. [05:34] What can businesses do to overcome some of these challenges? [05:42] We need a mindset change. We’re dealing with a different demographic of users online, and we’re dealing with a different type of fraud online when compared with offline transactions. [07:53] DataVisor recently launched a new offering on the Microsoft Azure marketplace, called DataVisor AI-Powered Fraud Management Solution. Tell us about it and how it addresses some of the challenges we just discussed. Yinglian: Using proprietary unsupervised machine learning algorithms, DataVisor restores trust in the digital era by enabling organizations to proactively detect and act on fast-evolving fraud patterns and prevent future attacks before they happen. Combining advanced analytics and an intelligence network of more than 4B global user accounts, DataVisor protects against financial and reputational damage across a variety of industries, including financial services, marketplaces, e-commerce, and social platforms. [10:39] How do you protect yourself from insider fraud? [13:37] How would a company use your solution with Azure? [14:33] How can customers find out more about the DataVisor AI-Powered Fraud Management Solution, and procure it through the Azure Marketplace? Yinglian: The best way to learn more about our solution is to go to the Microsoft Azure Marketplace and search for DataVisor. [15:06] How has partnering with Microsoft helped DataVisor scale and grow your business? [16:43] How do people connect with you? [17:09] Do you have any parting words of wisdom that you’d like to share with the audience? #AskTheCEO With Yinglian Xie

At this time, many strategic initiatives are being put on pause. The initiatives that tend to still have momentum are related to either driving efficiencies or reducing risk. And when it comes to risk, few are greater than regulatory risk. This week, we interview Yinglian Xie, CEO and co-founer of DataVisor. Yinglian discusses how AI fits into the compliance landscape in financial services. If you want to explore more AI use-cases across financial services and see what the big players in the sector are doing, you can use our AI Discovery tool with Emerj Plus. Learn more at emerj.com/plus

Take a deep dive into worms, spam, hijacked accounts, fraudulent transactions and more in this week's episode featuring Fang Yu, CTO of fraud detection platform DataVisor. Fang discusses her work developing algorithms and building systems for identifying malicious traffic, the process of co-founding a security startup and lessons learned from seven years at Microsoft.– Enter code “cyberwork” to get 30 days of free training with Infosec Skills: https://www.infosecinstitute.com/skills/– View transcripts and additional episodes: https://www.infosecinstitute.com/podcastFang started in the Microsoft cybersecurity research department with her DataVisor co-founder, Yinglian Xie, before the two started their company. Fang received her Ph.D. degree from the EECS Department at University of California at Berkeley. Her interests center on “big-data for security.” Over the past 10 years, she has been developing algorithms and building systems for identifying various malicious traffic such as worms, spam, bot queries, faked and hijacked account activities, and fraudulent financial transactions. Fang has published many papers at top security conferences and filed over 20 patents. Product wise, she has helped different online services combat large-scale attacks with multiple successful stories. DataVisor’s customers are an impressive bunch, they span the likes of Alibaba, Pinterest, LetGo, most major U.S. banking institutions and some of the largest Chinese insurance companies.About InfosecAt Infosec, we believe knowledge is the most powerful tool in the fight against cybercrime. We help IT and security professionals advance their careers with a full regimen of certifications and skills development training. We also empower all employees with security awareness and training to stay cybersecure at work and home. Founded by smart people wanting to do good, Infosec educates entire organizations on how to defend themselves from cybercrime. That’s what we do every day — equipping everyone with the latest security skills so the good guys win.

Yinglian Xie is the co-founder and CEO of DataVisor which is a fraud detection company powered by transformational AI technology. The company has raised $100 million from investors like NEA, Sequoia, GSR Ventures, and Genesis Capital. 

Yinglian Xie is the co-founder and CEO of DataVisor which is a fraud detection company powered by transformational AI technology. The company has raised $100 million from investors like NEA, Sequoia, GSR Ventures, and Genesis Capital. 

DataVisor discusses the rise in fraud during the holiday shopping season, as criminals target customer service retailers with such methods as reshipping fraud.

Yinglian Xie is CEO and Co-Founder of DataVisor, a leading Silicon Valley-based technology company providing advanced fraud management solutions powered by artificial intelligence. Founded in 2013, DataVisor empowers enterprise clients across the globe to proactively detect and defeat the most sophisticated modern attacks through the use of proprietary unsupervised machine learning algorithms, powerful big data architecture, and a robust suite of modeling and analytics solutions. Before founding DataVisor, Yinglian worked at Microsoft Research, where her focus was on advancing the security of online services with big data analytics and machine learning. Yinglian completed both her Ph.D. and post-doctoral work in Computer Science at Carnegie Mellon University, and currently holds over 20 patents in her field. A highly-regarded researcher, author, and conference contributor, Yinglian is widely regarded as one of the most influential figures in the areas of artificial intelligence, machine learning, and big data security.

No matter how you cut it, fraud can happen… especially in our increasingly digital world. Not only do payments businesses need to worry about this, but any organization with a digital presence also must be vigilant. Fortunately there are solutions to combat fraud… “good guys” out there fighting the good fight against “bad guys” with the help of technology. On this episode, we explore this with our guest, Priya Rajan, who is the Vice President of Marketing at DataVisor. DataVisor is actively working to leverage technology (such as machine learning), to help organizations manage fraud, fight spam and more. Priya had a tremendous amount to share about both the business costs of fraud, the challenges presented by fraudsters, and how technology is bridging the gap. Find show notes and more at: https://www.soarpay.com/podcast/

When it comes to fraud, the important thing is what you don’t know, said Yinglian Xie of DataVisor, a company that uses AI to help businesses deter fraudsters.

The theme for the entire month is AI for the customer experience in banking. In this episode, we speak with Yinglian Xie, CEO at Datavisor. Xie sheds light on how users will expect to have "zero-step" authentication, the "friction-free" future of banking. Xie paints a picture about how the experience consumers have with big tech (such as a Facebook app) can be transferred into banking. She gives a sense for how backend data can have a strong effect on how well banks can serve customers on the front end. Xie also talks about the value of new data sources as banks shift into the digital world.

The best approach to stop fraudsters, DataVisor says, is an effort uniting telecoms, merchants, machine learning technology and an educated, vigilant consumer.

DataVisor explains how deploying machine learning and AI is the best way to protect social media against online fraud and other such digital attacks.

“Existing solutions like supervised machine learning are very reactive to what the attacker is currently doing, so there's always a cat and mouse game; the unsupervised machine learning that we are building….doesn't have existing assumptions of what the fraud looks like, and that itself is actually more robust in terms of detection,” says Fang Yu, CTO and co-founder of DataVisor, a company whose mission is to protect large social and financial institutions from the increasing number of sophisticated cyber-attacks. When the nature of cyber-attacks can literally change on an hourly basis, the technology which relies upon the characteristics of past fraudulent behavior is insufficient. DataVisor's technology mitigates this problem by reviewing billions of accounts and identifying patterns of fraudulent behavior. Yu offers a detailed and informative conversation about DataVisor's services, which are currently protecting over four billion user accounts globally. She also discusses the advanced techniques used by fraudsters, the importance of early fraud detection, and an upcoming enterprise version of their technology which will allow clients to adjust the models themselves and have more leverage over the algorithms. Tune in, learn more by visiting datavisor.com, and email your questions to info@datavisors.com.

DataVisor says thieves will be busy this holiday shopping season on online marketplaces, seeking to monetize the stolen data that they've gathered.

DataVisor CEO says firms must step up AML solutions so AI and machine learning can fight online fraud in real time and secure bank data prior to cyberattacks.

GGV Capital’s Hans Tung and Zara Zhang interview Yinglian Xie and Fang Yu, the co-founders of DataVisor, a fast-growing startup in Silicon Valley that provides big data security analytics for consumer-facing websites and apps. Its customers include some of the largest companies in the world, such as Alibaba, Dianping, Pinterest, Yelp, and Bytedance (a.k.a. Toutiao), among others. Both Yinglian and Fang have decades of experience in internet security, specifically on fighting large-scale attacks to online services, such as fraudulent online payments, spamming, user hijacking, search-result poisoning, etc. They were both senior researchers at Microsoft for many years before starting DataVisor in 2013, and have filed over 20 patents. Yinglian received her Ph.D. in computer science from CMU and a Bachelor’s degree from Peking University. Fang holds a Ph.D. in computer science from Berkeley and a Bachelor’s degree from Fudan University. Join our listeners' community via WeChat/Slack at 996.ggvc.com/community. GGV Capital also produces a biweekly email newsletter in English, also called "996," which has a roundup of the week's most important happenings in tech in China. Subscribe at 996.ggvc.com. The 996 Podcast is brought to you by GGV Capital, a multi-stage venture capital firm based in Silicon Valley, Shanghai, and Beijing. We have been partnering with leading technology entrepreneurs for the past 18 years from seed to pre-IPO. With $3.8 billion in capital under management across eight funds, GGV invests in globally minded entrepreneurs in consumer internet, e-commerce, frontier tech, and enterprise. GGV has invested in over 280 companies, with 30 companies valued at over $1 billion. Portfolio companies include Airbnb, Alibaba, Bytedance (Toutiao), Ctrip, Didi Chuxing, DOMO, Hashicorp, Hellobike, Houzz, Keep, Musical.ly, Slack, Square, Wish, Xiaohongshu, YY, and others. Find out more at ggvc.com.

GGV Capital's Hans Tung and Zara Zhang interview Yinglian Xie and Fang Yu, the co-founders of DataVisor, a fast-growing startup in Silicon Valley that provides big data security analytics for consumer-facing websites and apps. Its customers include some of the largest companies in the world, such as Alibaba, Dianping, Pinterest, Yelp, and Bytedance (a.k.a. Toutiao), among others. Both Yinglian and Fang have decades of experience in internet security, specifically on fighting large-scale attacks to online services, such as fraudulent online payments, spamming, user hijacking, search-result poisoning, etc. They were both senior researchers at Microsoft for many years before starting DataVisor in 2013, and have filed over 20 patents. Yinglian received her Ph.D. in computer science from CMU and a Bachelor's degree from Peking University. Fang holds a Ph.D. in computer science from Berkeley and a Bachelor's degree from Fudan University. Join our listeners' community via WeChat/Slack at 996.ggvc.com/community. GGV Capital also produces a biweekly email newsletter in English, also called "996," which has a roundup of the week's most important happenings in tech in China. Subscribe at 996.ggvc.com. The 996 Podcast is brought to you by GGV Capital, a multi-stage venture capital firm based in Silicon Valley, Shanghai, and Beijing. We have been partnering with leading technology entrepreneurs for the past 18 years from seed to pre-IPO. With $3.8 billion in capital under management across eight funds, GGV invests in globally minded entrepreneurs in consumer internet, e-commerce, frontier tech, and enterprise. GGV has invested in over 280 companies, with 30 companies valued at over $1 billion. Portfolio companies include Airbnb, Alibaba, Bytedance (Toutiao), Ctrip, Didi Chuxing, DOMO, Hashicorp, Hellobike, Houzz, Keep, Musical.ly, Slack, Square, Wish, Xiaohongshu, YY, and others. Find out more at ggvc.com.

This week, IdentityMind Global raised $10M Series C, DataVisor raised $40M Series C, Infocyte raised $5.2 series B, and more business security news! Full Show Notes: https://wiki.securityweekly.com/BSWEpisode74 Visit http://securityweekly.com/category/ssw for all the latest episodes!

This week, IdentityMind Global raised $10M Series C, DataVisor raised $40M Series C, Infocyte raised $5.2 series B, and more business security news! Full Show Notes: https://wiki.securityweekly.com/BSWEpisode74 Visit http://securityweekly.com/category/ssw for all the latest episodes!

This week, Michael and Paul interview Joe Kay, Founder & CEO of Enswarm! In the Tracking Security Information segment, IdentityMind Global rasied $10M, DataVisor raised $40M, & Infocyte raised $5.2M! Last but not least, our second feature interview with Sean D'Souza, author of The Brain Audit! All that and more, on this episode of Business Security Weekly! Full Show Notes: https://wiki.securityweekly.com/BSWEpisode74   Visit https://www.securityweekly.com/bsw for all the latest episodes!

This week, Michael and Paul interview Joe Kay, Founder & CEO of Enswarm! In the Tracking Security Information segment, IdentityMind Global rasied $10M, DataVisor raised $40M, & Infocyte raised $5.2M! Last but not least, our second feature interview with Sean D'Souza, author of The Brain Audit! All that and more, on this episode of Business Security Weekly! Full Show Notes: https://wiki.securityweekly.com/BSWEpisode74   Visit https://www.securityweekly.com/bsw for all the latest episodes!

The O’Reilly Security Podcast: Sniffing out fraudulent sleeper cells, incubation in money transfer fraud, and adopting a more proactive stance.In this episode, O’Reilly’s Jenn Webb talks with Fang Yu, cofounder and CTO of DataVisor. They discuss sniffing out fraudulent sleeper cells, incubation in money transfer fraud, and adopting a more proactive stance against fraud.Here are some highlights: Catching fraudsters while they sleep Today's attackers are not using single accounts to conduct fraud; if they have a single account, the fraud they can conduct is very limited. What they usually do is construct an army of fraud accounts and then orchestrate either mass registration or account takeovers. Each of the individual accounts will then conduct small-scale fraud. They can do spamming, phishing, and all different types of malicious activity. But because they use many coordinated individual accounts, the attacks are massive in scale. To detect these, we take what is called an unsupervised machine learning approach. We do not look at individual users anymore—we take a holistic view of all the users and their correlations and linkage, and we use graph analysis and clustering techniques to identify these fraud rings. We can identity them even while they are sleeping. Hence, we call them ‘sleeper cells.’ Distinguishing bad from good is increasingly difficult The biggest threat we are facing right now is that fraudsters have almost unlimited resources and are equipped with advanced technologies. They can access cloud resources in a data center, for example, and they have underground markets with access to people specialized in creating new accounts, getting stolen credit cards, and taking over users’ existing accounts. In addition, they often have significantly more information than normal users would possess. For example, they can get credit reports and know exactly where a user lived three years ago, five years ago, and where they worked. The information they gather is very accurate, and that makes it easy for fraudsters to effectively impersonate a legitimate person. Accordingly, when online service providers see a request come in online, it's very hard for them to distinguish whether it is coming from a real user or a fraudster. Incubation in money transfer attacks When fraudsters set up different accounts for money transfers, they frequently start by testing small transactions. In the very beginning, it's all legitimate. They send small amounts to different users, and they use legitimate banking information, so there is no charge back. After that, they incubate for weeks or longer. After that incubation period, they use these accounts to conduct much larger transactions, because they’d already established the reputation for these accounts. Then, they begin conducting fraudulent transactions. That's one of the typical trends we see in our analysis. More than a quarter of fraudster accounts incubate, and many incubate a long time—more than 30 days before they start attacking. More than 11% attack after incubating more than 100 days. We saw one extreme case of a group of accounts that aged for more than three years before they started attacking. Moving from reactive to proactive detection At DataVisor, we do not want a point solution that only catches what attackers are already doing. That’s a cat and mouse game. We want to stay ahead of the game and know when fraudsters start doing something, or even anticipate when they’ll start before they do anything. We use data analytics to look at the behavior of attackers along with normal users, and extract fraudulent activities. Attackers have a lot of advanced techniques right now. They can go through two-factor authentication, and they have access to data centers. So, we use the latest technologies to defend against them and then to view the systems that they cannot invade—because, in the end, by looking at the attackers’ behavior, we can create a system that can detect and preempt fraud.

The O’Reilly Security Podcast: Sniffing out fraudulent sleeper cells, incubation in money transfer fraud, and adopting a more proactive stance.In this episode, O’Reilly’s Jenn Webb talks with Fang Yu, cofounder and CTO of DataVisor. They discuss sniffing out fraudulent sleeper cells, incubation in money transfer fraud, and adopting a more proactive stance against fraud.Here are some highlights: Catching fraudsters while they sleep Today's attackers are not using single accounts to conduct fraud; if they have a single account, the fraud they can conduct is very limited. What they usually do is construct an army of fraud accounts and then orchestrate either mass registration or account takeovers. Each of the individual accounts will then conduct small-scale fraud. They can do spamming, phishing, and all different types of malicious activity. But because they use many coordinated individual accounts, the attacks are massive in scale. To detect these, we take what is called an unsupervised machine learning approach. We do not look at individual users anymore—we take a holistic view of all the users and their correlations and linkage, and we use graph analysis and clustering techniques to identify these fraud rings. We can identity them even while they are sleeping. Hence, we call them ‘sleeper cells.’ Distinguishing bad from good is increasingly difficult The biggest threat we are facing right now is that fraudsters have almost unlimited resources and are equipped with advanced technologies. They can access cloud resources in a data center, for example, and they have underground markets with access to people specialized in creating new accounts, getting stolen credit cards, and taking over users’ existing accounts. In addition, they often have significantly more information than normal users would possess. For example, they can get credit reports and know exactly where a user lived three years ago, five years ago, and where they worked. The information they gather is very accurate, and that makes it easy for fraudsters to effectively impersonate a legitimate person. Accordingly, when online service providers see a request come in online, it's very hard for them to distinguish whether it is coming from a real user or a fraudster. Incubation in money transfer attacks When fraudsters set up different accounts for money transfers, they frequently start by testing small transactions. In the very beginning, it's all legitimate. They send small amounts to different users, and they use legitimate banking information, so there is no charge back. After that, they incubate for weeks or longer. After that incubation period, they use these accounts to conduct much larger transactions, because they’d already established the reputation for these accounts. Then, they begin conducting fraudulent transactions. That's one of the typical trends we see in our analysis. More than a quarter of fraudster accounts incubate, and many incubate a long time—more than 30 days before they start attacking. More than 11% attack after incubating more than 100 days. We saw one extreme case of a group of accounts that aged for more than three years before they started attacking. Moving from reactive to proactive detection At DataVisor, we do not want a point solution that only catches what attackers are already doing. That’s a cat and mouse game. We want to stay ahead of the game and know when fraudsters start doing something, or even anticipate when they’ll start before they do anything. We use data analytics to look at the behavior of attackers along with normal users, and extract fraudulent activities. Attackers have a lot of advanced techniques right now. They can go through two-factor authentication, and they have access to data centers. So, we use the latest technologies to defend against them and then to view the systems that they cannot invade—because, in the end, by looking at the attackers’ behavior, we can create a system that can detect and preempt fraud.

The O'Reilly Radar Podcast: Big data for security, challenges in fraud detection, and the growing complexity of fraudster behavior.This week, I sit down with Fang Yu, cofounder and CTO of DataVisor, where she focuses on big data for security. We talk about the current state of the fraud landscape, how fraudsters are evolving, and how data analytics and behavior analysis can help defend against—and prevent—attacks.Here are some highlights from our chat: Challenges in using supervised machine learning for fraud detection In the past few years, machine learning has taken a big role in fraud detection. There are a number of supervised machine learning techniques and breakthroughs, especially for voice, image recognition, etc. There's also an application for machine learning to detect fraud, but it's a little challenging because supervised machine learning needs labels. It needs to know what good users and bad users look like, and to know what good behavior is, what bad behavior is; the problem in many fraud cases is that attackers constantly evolve. Their patterns change very quickly, so in order to detect an attack, you need to know they will do next. That is ultimately hard, and in some cases—for example, financial transactions—it is too late. For supervised machine learning, you will have a charge back label from the bank because someone sees their credit card got abused and they called the bank. That's how you get the label. But that happens well after the actual transaction takes place, sometimes even months later, and the damage is already done. And moving forward, by the time you have a model to train to prevent it from happening again, the attacker has already changed his or her behavior. Supervised machine learning is great, but when applied to security, you need a quicker and more customized solution. An unsupervised machine learning approach to identify sleeper cells At DataVisor, we actually do things differently from the traditional rule-based or supervised machine learning-based approaches. We do unsupervised detection, which does not need labels. So, at a high-level, today's modern attackers do not use a single account to conduct fraud. If they have a single account, the fraud they can conduct is very limited. What they usually do is construct an army of fraud accounts, and then either do a mass registration or conduct account takeovers, then each of them will commit a little fraud. They can do spamming, they can do phishing, they can do all types of different bad activities. But together, because they have many accounts, they conduct attacks at a massive scale. For DataVisor, the approach we take is called an unsupervised approach. We do not look at individual users anymore. We look at all the users in a holistic view and uncover their correlations and linkages. We use graph analysis and clustering techniques, etc., to identify these fraudsters' rings. We can identify them even before they have done anything, or while they are sleeping, so we call them "sleeper cells." The big payoff of fraudulent faking Nowadays, we actually see fraud becoming pretty complex and even more lucrative. For example, if you look at e-commerce platforms, they sometimes offer reviews. They let users rate, like, and write reviews about products. And all of these can be leveraged by the fraudsters—they can write fake reviews and incorporate bad links in the writeups in order to promote their own products. So, they do a lot of fake likes to promote. Now, we also see a new trend going from the old days of having fake impressions, fake clicks now to actual fraudulent installs. For example, in the old days, when a gaming company had a new game coming out, they would purchase users to play these games—they would pay people like $50 dollars to play an Xbox game. Now, many of the games are free, but they need to drive installs to improve their rank in app stores. These gaming providers rely on app marketing, purchasing the users from different media sources, which can be pretty expensive—a few dollars per install. So, the fraudsters start to emulate the users and download these games. They are pretending they are media sources and cashing in by just downloading and playing the games. That payoff is 400 times more than that of a fake click or impression. The future of fraudsters and fraud detection Fraudsters are evolving to look more like real users, and it's becoming more difficult to detect them. We see them incubate for a long time. We see them using cloud to circumvent IP blacklists. We see them skirting two-factor authentication. We see them opening apps, making purchases, and doing everything a real, normal user does. They are committing fraud at a huge scale across all industries, from banking and money laundering to social, and the payoff for them is equally as massive. If they are evolving, we need to evolve, too. That's why new methods, such as unsupervised machine learning, are so critical to staying ahead of the game.

The O'Reilly Radar Podcast: Big data for security, challenges in fraud detection, and the growing complexity of fraudster behavior.This week, I sit down with Fang Yu, cofounder and CTO of DataVisor, where she focuses on big data for security. We talk about the current state of the fraud landscape, how fraudsters are evolving, and how data analytics and behavior analysis can help defend against—and prevent—attacks.Here are some highlights from our chat: Challenges in using supervised machine learning for fraud detection In the past few years, machine learning has taken a big role in fraud detection. There are a number of supervised machine learning techniques and breakthroughs, especially for voice, image recognition, etc. There's also an application for machine learning to detect fraud, but it's a little challenging because supervised machine learning needs labels. It needs to know what good users and bad users look like, and to know what good behavior is, what bad behavior is; the problem in many fraud cases is that attackers constantly evolve. Their patterns change very quickly, so in order to detect an attack, you need to know they will do next. That is ultimately hard, and in some cases—for example, financial transactions—it is too late. For supervised machine learning, you will have a charge back label from the bank because someone sees their credit card got abused and they called the bank. That's how you get the label. But that happens well after the actual transaction takes place, sometimes even months later, and the damage is already done. And moving forward, by the time you have a model to train to prevent it from happening again, the attacker has already changed his or her behavior. Supervised machine learning is great, but when applied to security, you need a quicker and more customized solution. An unsupervised machine learning approach to identify sleeper cells At DataVisor, we actually do things differently from the traditional rule-based or supervised machine learning-based approaches. We do unsupervised detection, which does not need labels. So, at a high-level, today's modern attackers do not use a single account to conduct fraud. If they have a single account, the fraud they can conduct is very limited. What they usually do is construct an army of fraud accounts, and then either do a mass registration or conduct account takeovers, then each of them will commit a little fraud. They can do spamming, they can do phishing, they can do all types of different bad activities. But together, because they have many accounts, they conduct attacks at a massive scale. For DataVisor, the approach we take is called an unsupervised approach. We do not look at individual users anymore. We look at all the users in a holistic view and uncover their correlations and linkages. We use graph analysis and clustering techniques, etc., to identify these fraudsters' rings. We can identify them even before they have done anything, or while they are sleeping, so we call them "sleeper cells." The big payoff of fraudulent faking Nowadays, we actually see fraud becoming pretty complex and even more lucrative. For example, if you look at e-commerce platforms, they sometimes offer reviews. They let users rate, like, and write reviews about products. And all of these can be leveraged by the fraudsters—they can write fake reviews and incorporate bad links in the writeups in order to promote their own products. So, they do a lot of fake likes to promote. Now, we also see a new trend going from the old days of having fake impressions, fake clicks now to actual fraudulent installs. For example, in the old days, when a gaming company had a new game coming out, they would purchase users to play these games—they would pay people like $50 dollars to play an Xbox game. Now, many of the games are free, but they need to drive installs to improve their rank in app stores. These gaming providers rely on app marketing, purchasing the users from different media sources, which can be pretty expensive—a few dollars per install. So, the fraudsters start to emulate the users and download these games. They are pretending they are media sources and cashing in by just downloading and playing the games. That payoff is 400 times more than that of a fake click or impression. The future of fraudsters and fraud detection Fraudsters are evolving to look more like real users, and it's becoming more difficult to detect them. We see them incubate for a long time. We see them using cloud to circumvent IP blacklists. We see them skirting two-factor authentication. We see them opening apps, making purchases, and doing everything a real, normal user does. They are committing fraud at a huge scale across all industries, from banking and money laundering to social, and the payoff for them is equally as massive. If they are evolving, we need to evolve, too. That's why new methods, such as unsupervised machine learning, are so critical to staying ahead of the game.