Leading Detection

Most fraud teams set alert thresholds with a finger in the wind. Kunal Datta thinks there’s a better way.

Is it machine learning or rules? Kunal Datta, Chief Product Officer at Unit21, says you don’t have to choose. Fresh from Money20/20, Kunal joins Matt Brady to talk about why “signals over scores” beats a mystery fraud number, how AI can tune rules from as few as 10 examples, and why trust in AI agents has to be earned step by step. We also cover how scammers use AI to run a thousand pig butchering scams at once, and why using AI in fin crime is a moral duty.

Chapters:
00:00 Setting alert thresholds with a finger in the wind00:59 Welcome and Money20/20 recap02:19 Where machine learning earns its keep04:39 Where machine learning starts to crack07:46 Rules: clear logic and catching new behaviour08:45 Getting the best of rules and AI12:45 Signals over scores15:09 Gut feel, decision instructions and real vs written SOPs17:32 Building trust in AI: progressive autonomy21:54 Who’s moving fastest: crypto vs banks24:50 The risk of leaner teams and AI doing the legwork30:10 How scammers are using AI34:07 Quick fire: ML, rules and gen AI34:42 Agent payments and new types of disputes36:27 The Anthropic IPO38:06 Where to find Kunal

Resources:

• Kunal’s article, “A finger in the wind: How institutions decide which crimes to ignore”: https://www.unit21.ai/blog/a-finger-in-the-wind-how-institutions-decide-which-crimes-to-ignore
• Unit21: https://unit21.ai
• Kunal on LinkedIn: https://www.linkedin.com/in/kunal-datta/

Watch and listen:

• YouTube: https://www.youtube.com/channel/UC8Gm5R039pPnJqS27QdvYlw/
• Apple Podcasts: https://podcasts.apple.com/us/podcast/leading-detection/id1854719167

More from Sedulo Search:

• Website: https://sedulo.io
• LinkedIn: https://www.linkedin.com/company/sedulo-search/
• Follow Matt Brady: https://www.linkedin.com/in/mattbrady-sedulo/

Sedulo Search is a retained recruitment firm that places product, ML, engineering and solutions talent in fraud prevention. If you’re hiring or looking for your next role in fraud, get in touch: https://sedulo.io

Over half of job applicants could be fake, and bots now make up more than 70% of internet traffic. Persona co-founder and CTO Charles Yeh joins Matt to talk about deepfakes, digital twins and how we prove who's real online. Plus, why the future of fraud prevention is less about catching bad actors and more about protecting the humans.

► Subscribe to the Leading Detection Podcast: @sedulo_search

► Listen on Spotify: https://open.spotify.com/show/6ci2UpvNNmaLBrXimQ9pe3?si=pF2pE-0GS-6woZCZuhnejQ

► Listen on Apple Podcasts: https://podcasts.apple.com/us/podcast/leading-detection/id1854719167

More from Sedulo Search - Technical Talent For Fraud Prevention:

► Website: https://www.sedulo.io

► LinkedIn: https://www.linkedin.com/company/sedulo-search/

► Follow Matt Brady: https://www.linkedin.com/in/mattbrady-sedulo/

Sedulo Search is a retained recruitment firm that places product, ML, engineering, and solutions talent in fraud prevention. If you're hiring or looking for your next role in fraud, get in touch: https://www.sedulo.io/fraud-insights#collaboration

Summary

In this episode, Charles, CTO at Persona, discusses the evolving landscape of digital identity verification, fraud detection, and the challenges posed by increasingly sophisticated AI-generated fake identities and videos. Learn about the latest techniques in combating candidate fraud, deepfakes, and the future of digital IDs.

Key Topics

• The rise of candidate fraud and synthetic identities
• Multimodal fraud detection techniques combining computer vision and social profile analysis
• The complexity of deepfake and video manipulation attacks
• Layered fraud attack vectors and adaptive defenses
• The future of digital IDs and the shift towards digital identity verification
• Balancing security, user experience, and trust in online platforms
• The impact of AI-generated content on fraud detection
• Strategies for reducing friction for legitimate users while blocking fraudsters
• The importance of ensemble models and multimodal signals in fraud detection
• The societal and technical challenges of moving towards fully digital IDs

Chapters

00:00 Introduction to digital identity challenges

00:22 The complexity of candidate fraud

01:24 Types of identity fraud and synthetic identities

02:33 Multimodal fraud detection techniques

03:12 Balancing security and user experience

04:07 Risks of candidate fraud for companies

05:10 Attack vectors: identity muling and digital twinning

06:49 The rise of sophisticated deepfakes

11:49 Using ensemble models for fraud detection

15:20 Layered attack techniques and countermeasures

20:01 Segmentation and risk-based verification

22:13 Reducing friction for legitimate users

27:04 The future of digital IDs and AI advancements

Keywords

digital identity, fraud detection, deepfakes, computer vision, AI, digital IDs, identity fraud, biometric verification, cybersecurity, online safety

#DigitalIdentity #BiometricVerification #Deepfakes #FraudDetection #Cybersecurity

After two decades fighting fraud at Google, Facebook, and Square, Kevin Lee (now CTO, Trust & Safety at Sift) sits down to explain why he builds every system with one customer in mind: the fraudster. He talks about silos, the coming headcount reckoning, and why trust & safety is quietly becoming a company's biggest growth lever.

► Subscribe to the Leading Detection Podcast: @sedulo_search

► Listen on Spotify: https://open.spotify.com/show/6ci2UpvNNmaLBrXimQ9pe3?si=pF2pE-0GS-6woZCZuhnejQ

► Listen on Apple Podcasts: https://podcasts.apple.com/us/podcast/leading-detection/id1854719167

More from Sedulo Search - Technical Talent For Fraud Prevention:

► Website: https://www.sedulo.io

► LinkedIn: https://www.linkedin.com/company/sedulo-search/

► Follow Matt Brady: https://www.linkedin.com/in/mattbrady-sedulo/

Sedulo Search is a retained recruitment firm that places product, ML, engineering, and solutions talent in fraud prevention. If you're hiring or looking for your next role in fraud, get in touch: https://www.sedulo.io/fraud-insights#collaboration

Kevin Lee shares his extensive experience in trust and safety, exploring how fraud and abuse have evolved in the digital age, the importance of holistic approaches, and the future of AI in combating digital threats.

Key Topics

• Evolution of trust and safety over two decades
• Expansion of fraud vectors beyond payment fraud
• The role of policy and regulation in trust and safety
• Adversarial mindset of bad actors and system design
• The importance of holistic, integrated fraud prevention systems
• The impact of AI and data fragmentation on trust and safety
• Talent and organisational evolution in trust and safety teams
• The role of vendors and industry consolidation
• Future predictions for trust and safety in a rapidly evolving landscape

Chapters

00:00 Introduction and Kevin's background

01:16 The evolution of fraud from credit card theft to account takeover

02:07 The interconnected nature of abuse vectors

03:16 Growth and expansion of trust and safety concerns

04:20 Policy, regulation, and industry accountability

05:34 The convergence of fraud and trust safety

07:15 Adversarial mindset and system design for fraud prevention

08:34 Organizational silos and the need for integration

10:00 Industry collaboration and sharing best practices

11:46 Accountability and blame in trust and safety

13:50 Human expertise and AI in fraud detection

16:54 Limitations of technology and the human element

18:51 Differentiating real from fake in AI-generated content

20:55 Data fragmentation and its impact on trust and safety

22:18 Talent evolution and team skills in trust and safety

24:35 From reactive to proactive fraud prevention

27:32 The role of technology versus people in trust and safety

28:45 Building a trust and safety stack for the future

34:00 Industry consolidation and vendor ecosystem

35:27 Near-term and long-term predictions for trust and safety

#TrustAndSafety #AI #DigitalTrust #FraudPrevention #AccountTakeover

Shuman Ghosemajumder, ex-Google and former CTO at Shape Security, now founder of REKEN, joins Matt to explain why the internet was never built for trust, and how AI is supercharging both scams and the tools to fight them. From deepfake phishing to "agents talking to agents," they explore what a trustworthy internet could look like and why on-device AI may be the answer.

► Subscribe to the Leading Detection Podcast: @sedulo_search

► Listen on Spotify: https://open.spotify.com/show/6ci2UpvNNmaLBrXimQ9pe3?si=pF2pE-0GS-6woZCZuhnejQ

► Listen on Apple Podcasts: https://podcasts.apple.com/us/podcast/leading-detection/id1854719167

More from Sedulo Search - Technical Talent For Fraud Prevention:

► Website: https://www.sedulo.io

► LinkedIn: https://www.linkedin.com/company/sedulo-search/

► Follow Matt Brady: https://www.linkedin.com/in/mattbrady-sedulo/

Sedulo Search is a retained recruitment firm that places product, ML, engineering, and solutions talent in fraud prevention. If you're hiring or looking for your next role in fraud, get in touch: https://www.sedulo.io/fraud-insights#collaboration

In this episode, Shuman discusses the evolving trust infrastructure of the internet, the impact of AI on online trust, and how to build a safer, more trustworthy digital environment. We explore the challenges of AI-generated content, fraud prevention, and future solutions for a zero-trust internet.

Key Topics

• The impact of AI on online trust and misinformation

• The evolution of internet trust from military to public use

• Fraud and cybercrime targeting large user bases

• The importance of trust signals and indicators

• AI-generated content and its implications for trust

• Future solutions for a zero-trust internet

• On-device analysis for secure communication

• Building trust through transparency and privacy

Chapters

00:00 Introduction and guest background

00:41 Why trust on the internet is a growing concern

01:00 AI's role in exacerbating trust issues

02:20 The lack of trust infrastructure on the internet

03:19 Historical trust in the early internet

07:41 Different types of distrust and trust evolution

09:04 The role of encryption in building trust

10:30 Visual cues and user awareness of fraud

12:13 Banner blindness and user behaviour

14:07 The ineffectiveness of traditional phishing training

17:23 The need for AI-driven trust solutions

18:46 Envisioning a trusted internet with AI and trust indicators

22:10 The importance of trust indicators for AI content

24:41 Media and AI-generated content

30:55 Upgrading communication infrastructure for trust

34:21 On-device analysis and real-time protection

36:06 Building a safer internet for humans

37:40 The concept of a zero-trust internet

38:46 The mindset for a trust-based digital future

40:43 Conclusion and future outlook

#Cybersecurity #AISafety #AIGeneratedContent #OnlineFraud #DigitalSecurity

Michael Jabbara, SVP at Visa, joins the show to break down VAMP (Visa's Acquirer Monitoring Program): what it is, why Visa built it, and what merchants and acquirers actually need to do to stay compliant. He shares real data showing that fixing fraud and dispute issues doesn't hurt growth; it actually boosts approval rates and helps businesses grow faster.

► Subscribe to the Leading Detection Podcast: @sedulo_search

► Listen on Spotify: https://open.spotify.com/show/6ci2UpvNNmaLBrXimQ9pe3?si=pF2pE-0GS-6woZCZuhnejQ

► Listen on Apple Podcasts: https://podcasts.apple.com/us/podcast/leading-detection/id1854719167

More from Sedulo Search - Technical Talent For Fraud Prevention:

► Website: https://www.sedulo.io

► LinkedIn: https://www.linkedin.com/company/sedulo-search/

► Follow Matt Brady: https://www.linkedin.com/in/mattbrady-sedulo/

Sedulo Search is a retained recruitment firm that places product, ML, engineering, and solutions talent in fraud prevention. If you're hiring or looking for your next role in fraud, get in touch: https://www.sedulo.io/fraud-insights#collaboration

Summary

In this episode, we explore the Visa Acquire Monitoring Program (VAMP), a crucial initiative to combat outlier fraud and dispute behaviour in digital payments. Michael Jabbara from Visa shares insights on how VAMP works, its impact on growth and security, and how merchants and acquirers can leverage it for long-term success.

Key Topics

• VAMP's purpose and origin
• How VAMP detects outlier fraud and disputes
• Impact of VAMP on merchant growth and security
• Thresholds and remediation strategies in VAMP
• Evolving threats in digital payments and future predictions

Chapters

00:00 Introduction to the episode and guest

02:22 What is VAMP and its origins

03:23 Design and evolution of the Visa Acquire Monitoring Program

04:18 Thresholds and incentives for upstream controls

05:21 Why digital payments growth necessitated VAMP

06:11 Early results and learnings from VAMP implementation

07:29 Impact of thresholds on merchant growth and risk

08:43 Remediation strategies and long-term benefits

10:19 False positives and improving approval rates

11:10 The relationship between risk, security, and growth

12:44 Operational differences before and after VAMP

13:31 Explaining VAMP to merchants and acquirers

15:06 Control frameworks and best practices for fraud prevention

16:52 Global consistency and regional adjustments

18:36 The importance of evolving fraud prevention programs

20:25 Cardholder impact and fraud behavior

22:27 Future trends and program evolution

24:39 Advising on upstream controls and best practices

28:48 Summary of VAMP's benefits for merchants and acquirers

29:56 Final thoughts and resources for further information

#VisaVAMP #FraudPrevention #DigitalPayments #PaymentSecurity #RiskManagement

Hanjo Seibert, Managing Director of Risk & Compliance and TED speaker, joins Leading Detection to break down why fraudsters are innovating faster than the institutions meant to stop them — and why fixing it comes down to data, agile teams, and bold leadership, not just technology.

► Subscribe to the Leading Detection Podcast: @sedulo_search

► Listen on Spotify: https://open.spotify.com/show/6ci2UpvNNmaLBrXimQ9pe3?si=pF2pE-0GS-6woZCZuhnejQ

► Listen on Apple Podcasts: https://podcasts.apple.com/us/podcast/leading-detection/id1854719167

More from Sedulo Search - Technical Talent For Fraud Prevention:

► Website: https://www.sedulo.io

► LinkedIn: https://www.linkedin.com/company/sedulo-search/

► Follow Matt Brady: https://www.linkedin.com/in/mattbrady-sedulo/

Sedulo Search is a retained recruitment firm that places product, ML, engineering, and solutions talent in fraud prevention. If you're hiring or looking for your next role in fraud, get in touch: https://www.sedulo.io/fraud-insights#collaboration

Episode summary

In this episode, Hanjo Seibert discusses the evolving landscape of fraud detection and prevention, the impact of technological innovation, and strategic approaches for financial institutions to stay ahead in the fight against fraud.

Key Topics

• Evolution of fraud detection over the past decade
• Impact of generative AI and automation on fraud schemes
• Strategies for agile implementation of fraud prevention tools
• The importance of organisational culture and leadership in innovation
• Differentiating between fraud and AML challenges
• The significance of data-driven insights in fraud detection
• Client interaction design as a fraud prevention measure
• Predictions for fraud trends in the next 12-24 months

Chapters

00:00 Introduction and guest background

02:25 Evolution of fraud detection over 10 years

04:37 Challenges of outdated solutions and implementation timelines

06:02 Shortening timelines as an advantage for market winners

07:27 Fraud innovation versus regulatory constraints

08:47 Fraud as a sandbox for broader compliance innovation

10:17 External factors and social engineering in fraud

11:38 Designing customer journeys with fraud controls

13:53 Real-time fraud detection challenges

17:29 Industry questions on scams and client education

19:33 Leveraging technology and AI in fraud schemes

22:49 Advising clients on fraud and technology strategies

25:10 Growing fraud problem and industry awareness

27:03 Barriers to innovation: change management and culture

28:25 Designing future-proof fraud prevention architectures

30:28 Outlook for the next 12-24 months

32:21 Leadership and organisational change for fraud innovation

34:48 The role of executive leadership in driving change

36:00 Predictions for fraud trends and technological advances

38:03 Closing remarks and contact information

#FraudDetection #FinancialTechnology #AI #AML #FraudPrevention

Deepanker joins us to discuss the evolution of identity verification, the challenges of fraud in digital spaces, and the future of adaptive security measures. This episode explores how technology and behavioural signals are reshaping trust and security in online transactions.

Key Topics

• The evolution of identity verification from face-to-face to digital
• The impact of technology on fraud methods and detection
• The importance of behavioural signals in security
• The role of context and continuous verification in fraud prevention
• Emerging risks like age assurance and workforce fraud

Chapters

00:00 Introduction to Deepanker Saxena and IDV

02:04 The impact of technology on fraud methods

04:22 The rise of remote fraud and technological countermeasures

06:30 The importance of multi-vector verification

09:09 The role of context in fraud detection

11:21 The significance of platform-wide context and history

13:42 Predictive models and understanding user behaviour

15:20 Continuous identity verification throughout the customer lifecycle

17:12 Seamless user experience with subtle signals

20:10 The rise of age assurance and its importance

21:26 Risks associated with digital age verification

22:56 Emerging risks in workforce verification

24:38 Fraud rings and sophisticated workforce fraud tactics

27:04 The ongoing evolution of fraud tactics

27:59 The concept of agentic fraud and prompt injections

29:31 The importance of binding identity to agents

32:20 The future of identity and agent-based verification

33:19 Building a comprehensive ecosystem of identities

34:14 The impact of agent-based systems on daily life

35:20 Emerging trends and future challenges in identity verification

#cybersecurity #techpodcast #digitalidentity #fraudprevention #biometrics

In this episode, Colin Parsons from Nasdaq Verafin discusses the current state of financial crime, the impact of AI on fraud, and innovative strategies for detection and prevention. Discover how industry leaders are adapting to rapid changes and leveraging new technologies to combat fraud effectively.

Key Topics

• Rise in global financial crime to 4.4 trillion annually
• Increase in authorised scam losses by 19.3% over two years
• Shift from human-scale to machine-scale fraud driven by AI
• Importance of network data and consortium insights in detection
• Proactive fraud prevention beyond real-time transaction analysis
• Role of agentic AI in enhancing investigator efficiency
• The impact of AI models and agentic AI workforce in fraud detection
• Future trends: more scams, credential stuffing, and vulnerabilities

Chapters

00:00 Introduction and guest introduction

00:44 Current mood among fraud teams and industry uncertainty

02:07 Overview of the global financial crime report

03:06 Rise in financial crime and fraud losses

04:40 Impact of AI on fraud and scams

06:11 Shift to machine-scale fraud and deep fake scams

07:09 Factors driving increased sophistication and volume of fraud

09:07 Shift from cyber to human scam focus

10:32 Education and friction in fraud prevention

12:22 Using data and context to identify scams earlier

15:08 Network approach and consortium data in fraud detection

18:22 Real-time vs proactive fraud prevention strategies

19:13 Leveraging AI to filter signals and reduce noise

20:40 Unified view for investigators and AI models

21:20 Role of agentic AI in fraud investigation

23:36 Adoption and surprises with agentic AI workforce

25:38 Combining AI with network insights for effectiveness

26:25 Predictions for the next 6-12 months in fraud

28:11 Resources and contact information for further learning

#financialcrime #fraudprevention #ai #cybersecurity #fintech

In this episode, Eugeny Malyutin from SUMSUB discusses the realities and hype around AI and ML in fraud prevention, exploring how fraud tools have democratised, the current state of AI in fighting fraud, and best practices for deploying AI systems in regulated environments.

Key Topics

• The democratisation of fraud tools and its implications
• Current state and future of AI and ML in fraud detection
• Best practices for deploying AI in regulated environments
• The role of human oversight in AI-driven fraud prevention
• Challenges and opportunities with generative AI and deepfakes

Chapters

00:00 Introduction to the episode and guest

03:06 Hype versus reality in AI-driven fraud agents

08:00 Differences in applying ML in fraud versus other industries

12:04 Building a modern, multi-model fraud detection system

14:15 Speed of fraud evolution and detection challenges

15:12 Data versus models: what is more important?

16:22 Detecting new fraud patterns with data and AI

17:02 Automating data labeling and improving models

18:33 Balancing fraud detection and customer experience

21:46 From demo to production in regulated environments

22:17 Regulatory requirements for AI in fraud detection

23:19 The importance of infrastructure and continuous evaluation

24:11 What typically breaks when scaling AI systems

25:41 Reducing confidence errors in large language models

28:35 Generative AI's role in fraud detection and analysis

29:50 Using AI for document analysis and environment configuration

33:22 The hype around generative AI and its limitations

34:19 Hiring for AI and ML in fraud prevention

36:44 Onboarding new talent from other domains

38:20 Eugeny's outlook for AI in the second half of the year

#AI #Cybersecurity #FraudDetection #Deepfakes #GenerativeAI

In this episode, Pedro Sanzovo shares his journey into fraud prevention, the evolving role of AI, and how data-driven strategies are shaping the future of anti-fraud technology. Discover insights on balancing AI advancements with fraud defence and the importance of curiosity in this dynamic field.

Key topics

• Pedro's journey into fraud prevention
• The role of open banking in fraud detection
• AI advancements and challenges in fraud prevention
• Data assets and their impact on fraud defence
• The future of fraud products and industry trends

Chapters

00:00 Introduction and Pedro’s journey into fraud

02:04 Starting in AML and fraud prevention at Palantir

04:10 Founding a fraud prevention company in Brazil

06:05 Acquisition by Signified and role in fraud at checkout

07:46 Data infrastructure and the evolution of fraud detection

09:58 Open banking’s influence on fraud prevention

12:00 The importance of quality data and layered defences

13:51 Balancing AI advancements with fraud prevention challenges

15:48 Technologies like deepfakes and evolving fraud tactics

18:00 The ongoing battle against fraud and AI’s role

20:02 Leveraging AI to empower investigators and improve defences

21:57 Transforming fraud decisioning with sequential models

24:06 Change management and industry adoption of new tech

26:06 The future of fraud as a growth enabler

28:01 The blurring lines between fraud, credit, and marketing

29:57 Emerging trends: first-party fraud and industry evolution

32:05 Final thoughts and Pedro’s advice for aspiring fraud professionals

#FraudPrevention #AIInFraud #DataDrivenSecurity #OpenBanking #FraudDetectionStrategies