Fraudology Podcast with Karisse Hendrick

In this episode, I'm sitting down with Tal Yeshanov. Someone I've known for a very long time in this industry, and one of the sharpest risk leaders I know. Tal's path into fraud started almost by accident at Google and YouTube. Then took her through building fraud programs at Eventbrite, before its IPO, and Uber during its earliest hockey-stick growth years. Tal has spent her career building holistic fraud detection systems from scratch, in industries where there was no playbook to follow.
For years, fraud teams operated off a snapshot. Device at checkout. IP at checkout. Did the payment information match? Tal walks through why that single-moment view is no longer enough. And why the shift toward an orchestration platform, one that pulls in customer journey risk signals from the moment a user lands on your site rather than just the moment they transact, is where modern fraud programs are actually headed.
The deeper theme of this episode is what happens when you stop treating fraud detection as a scoring exercise, and start treating it as a full picture. Tal shares a personal story about a rule she built early in her career that was, on paper, flawless. It caught the exact triangulation fraud pattern it was designed for. It also caught a company executive, because his girlfriend used his credit card in a different city. That's false positive reduction in fraud detection in its most human form, and it's a direct argument for upstream fraud prevention data collection: pulling in more signals earlier in the journey instead of adding more rules at the transaction point.
What you'll hear in this episode:
How Tal moved from Google and YouTube into building fraud programs at Eventbrite and Uber with no existing playbook to follow.
Why holistic fraud detection means tracking customer journey risk signals from first visit to transaction, not just a snapshot at checkout.
How an orchestration platform unifies device, IP, email, and behavioral data that used to live in separate point solutions.
A real story about false positive reduction in fraud detection, including a rule that was technically perfect and still failed a legitimate customer.
How the same holistic approach extends to account takeover detection, including typing cadence, autofill behavior, and device history.
Why domain expertise vs AI in fraud isn't a competition, and how agentic AI is being used right now to query databases, support customer service teams, and triage escalations.
A candid conversation about AI replacing fraud jobs, including a real example of a company that prematurely laid off its fraud leadership.
Why fraud team tribal knowledge doesn't transfer to an AI model, and what companies risk losing when it walks out the door.
Tal's fraud leadership philosophy, built on transparency and empathy, and why it creates teams that stay in touch for years.
The ongoing industry shift from risk team vs fraud team naming, and why more companies are choosing the broader term.

You should listen to this episode if you:
Work in fraud detection, risk operations, account security, or trust and safety.
Are evaluating an orchestration platform or trying to move your fraud program beyond point-in-time scoring.
Want a practical, non-hypothetical look at where agentic AI actually fits in fraud operations today.
Are a fraud leader worried about AI replacing fraud jobs on your team, or trying to make the case for why domain expertise still matters.
Care about fraud leadership philosophy and want to build a team that stays loyal and stays sharp.

Welcome back to Fraudology.
Every once in a while I come across a report that makes me stop what I was planning to talk about because it's just that important. This is one of those weeks.
Matt Vega recently released his quarterly fraud report 2026, and after reading it, I knew we needed to break it down together. Not because it's predicting what might happen next year. Because every attack covered in this report is already happening.
One of the biggest themes running through the report is that fraud is simply moving faster than fraud teams are. AI is making sophisticated attacks cheaper, easier to launch, and much harder to detect. Criminals no longer need deep technical skills when they can rent the tools they need through fraud as a service marketplaces.
So what does that actually look like?
In this episode, I walk through several of the newest fraud tactics already showing up in the wild, including malware hidden behind fake unsubscribe links, banking malware that can piggyback on a customer's trusted device, and session hijacking techniques that make account takeover fraud incredibly difficult to detect using traditional fraud detection models.
At first glance, many of these attacks look legitimate. That's exactly the problem.
We also talk about why fraud teams can't rely on individual trust signals like device intelligence, IP reputation, or even behavioral analytics by themselves anymore. Criminals have learned how to blend into legitimate customer behavior, which means our approach to fraud detection and fraud prevention has to evolve too.
This is where things get interesting.
One of my biggest takeaways from Matt's report is that the answer isn't one new tool or one new model. It's layering better fraud intelligence, sharing information across consortium networks, and understanding the broader cybercrime trends happening outside your own organization. Because by the time a new attack reaches your queue, there's a good chance another company has already seen it.
I also spend a few minutes sharing an update on the Merchant Fraud Alliance conference, including our new AI bootcamp that's focused on practical ways fraud teams can start using AI in fraud prevention today. Not because AI replaces fraud analysts, but because it helps good teams move faster.
If you work in merchant fraud, banking fraud, online fraud, or e-commerce fraud, this is one of those episodes that will help you recognize the patterns before they become your next incident.
What you'll hear in this episode:
Why Matt Vega's quarterly fraud report 2026 is one of the most valuable fraud intelligence resources released this year.
How AI is accelerating modern cybercrime and making sophisticated attacks accessible through fraud-as-a-service platforms.
A breakdown of several emerging fraud tactics already targeting merchants and financial institutions.
How unsubscribe phishing campaigns are being used to install malware and keyloggers.
Why banking malware is becoming increasingly effective at bypassing traditional fraud controls.
How session hijacking enables criminals to perform account takeover fraud from trusted customer devices.
Why device intelligence, IP reputation, and behavioral analytics all need to be evaluated together instead of independently.
How fraud intelligence sharing and consortium data help organizations identify emerging threats faster.
An update on the Merchant Fraud Alliance conference and its new AI in fraud prevention bootcamp.

You should listen to this episode if you:
Lead fraud, risk, or trust & safety teams.
Manage fraud prevention for an ecommerce merchant, fintech, bank, or payments company.
Want to stay ahead of the latest cybercrime trends instead of reacting after attacks become widespread.
Are evaluating how AI is changing both fraud prevention and AI fraud.
Build or manage fraud detection models.
Investigate account takeover, synthetic identity, or online fraud.
Want practical fraud prevention best practices instead of theoretical discussions.
Rely on device intelligence, IP reputation, or behavioral analytics as part of your fraud strategy.

Welcome back to Fraudology.
In this episode, I’m sitting down with Mark Porteous, a longtime leader in e-commerce fraud and trust who knows two-sided marketplaces from the inside out. Mark spent nine years at StockX, where he started in customer support before building the company’s fraud program from the ground up. And honestly, that is one of the best ways to learn marketplace fraud prevention because you see the customer complaints, the chargebacks, the seller issues, the account problems, and the policy gaps before anybody has officially decided they belong to a fraud team.
We get into what makes online marketplace fraud so different from traditional e-commerce. In a standard retail transaction, the merchant controls the inventory, the pricing, and fulfillment. In a two-sided marketplace, the platform may be trusting one person to sell, another person to buy, and sometimes a third person to deliver the product. Every additional participant creates another identity question, another fraud vector, and another opportunity for marketplace scams or policy abuse.
The deeper theme of this episode is market volatility fraud. Prices can change dramatically because of a sports result, a viral release, an artist announcement, a celebrity event, or a sudden shortage. When that happens, legitimate customer behavior changes, but fraudulent behavior changes too. Sellers may decide not to fulfill because they can resell the item for more. Buyers may file friendly fraud chargebacks after prices fall. Stolen cards may be used to purchase high-demand inventory. And risk models that normally work well can suddenly start treating good customers like fraudsters.
Marketplace fraud prevention cannot stay on autopilot. Fraud leaders need strong policies, clear escalation playbooks, reliable fraud intelligence, and real collaboration with vendors, data teams, customer support, marketing, product, and leadership.

What you’ll hear in this episode:
How Mark moved from customer support into building a marketplace fraud program from the ground up.
Why two-sided and multi-sided marketplaces create more complex identity, payment, seller, and fulfillment risks.
How marketplace pricing volatility can trigger seller non-fulfillment, policy abuse, first-party fraud, and chargebacks.
Why World Cup ticket pricing is a real-time example of market volatility fraud.
How friendly fraud can increase when buyers repurchase the same item after its secondary-market price drops.
Why fraud models and vendor strategies cannot be left on autopilot during high-demand events.
How approval rates, false declines, fraud risk scoring, and card-not-present fraud need to be balanced during sudden demand spikes.
Why fraud leaders need playbooks, policy enforcement, and clear escalation paths before an unexpected event happens.
How to work with marketing, product, growth, finance, customer support, and security without becoming the team that says no to everything.
Why strong fraud storytelling must always be supported by fraud analytics and measurable business impact.

You should listen to this episode if you:
Work in marketplace fraud prevention, trust and safety, fraud operations, or fraud risk management.
Manage buyer fraud, seller fraud, marketplace chargebacks, seller verification, or payment fraud prevention.
Work for a ticketing, sneaker, collectible, resale, delivery, or multi-sided marketplace.
Need a better approach to fraud monitoring during major events, product releases, shortages, or pricing spikes.
Want to improve collaboration between fraud, customer support, product, growth, marketing, finance, and security teams.

In this episode of Fraudology, Karisse Hendrick provides a comprehensive debrief following the massive shifts in the world of artificial intelligence and digital fraud. Karisse shares her highlights and lowlights from navigating the industry's rapid evolution, cutting through the future-looking hype to provide practical insights for fraud and payments professionals.
The conversation explores the evolving mechanics of Agentic AI in commerce, detailing how partnerships like the new Visa and OpenAI infrastructure are designed to make AI commerce a reality. Karisse provides an inside look at why OpenAI previously shelved its original agentic project to avoid becoming a merchant of record, shifting away from full structural ownership due to complex liability rules and low initial adoption.
We also explore the "hot topics" dominating the fraud landscape today:
The VAMP Threshold "Cliff": How Visa’s monitoring programs offer no "trial" or "safety" months anymore, immediately penalizing merchants the first month they cross thresholds with instant fines and fees per chargeback and TC40.
The Complexity of Agentic Chargebacks: Real-world examples of "authorized" AI purchases where merchants are automatically losing disputes because card brands do not yet have established "compelling evidence" rules or representment provisions for AI agents.
The Hook of Cloned Sites: Why AI models looking purely for the "best deal" are inadvertently leading consumers straight into elaborate, cloned phishing websites that harvest credit card data and trigger fraudulent descriptors.

Additionally, Karisse dives into the latest real-world data from a recent UK case study highlighting how fraudulent duplicate sites for household brands appeared directly inside ChatGPT's search indexes. We break down the immediate operational steps fraud leaders must take to protect their customer service channels and coordinate with IT to combat malicious DNS activity before these automated losses skyrocket.

In this episode of Fraudology, Karisse Hendrick sits down with Hailey Windham, Community Lead for Banking at Sardine and host of the Fraud Forward podcast. Hailey shares her journey transitioning from a practitioner at community financial institutions to the vendor side, focusing entirely on providing practical, operational insights for credit unions and community bank fraud teams.
The conversation explores the highly anticipated June 2026 updated guidance from FinCEN regarding Section 314B of the USA Patriot Act. Hailey breaks down how this new fact sheet eliminates long-standing confusion and regulatory fears, giving financial institutions a robust legal framework to safely share information and collaborate under a liability safe harbor.
We also explore the "hot topics" dominating the banking fraud landscape today:
Fraud Explicitly in Scope: How the new guidance expands past narrow money laundering limits to formally include computer fraud and scams targeting individuals, organizations, or governments.
Reasonable Suspicion vs. Certainty: Why teams no longer need a fully completed investigation or total certainty before sharing data, making early sharing on incomplete information permissible.
Real-Time Data Transmission: The protocol shifts allowing financial institutions to share verbal alerts, video surveillance footage, IP addresses, and attempted transactions in real time.
The Power of Associations: How non-bank compliance providers and industry trade groups can now legally organize 314B associations so smaller institutions don't have to fight fraud alone.

Additionally, Hailey dives into the preliminary insights from the industry’s first practitioner-built benchmarking survey for community banks and credit unions under $10 billion. We examine the systemic issues keeping banking fraud fighters up at night, from rigid legacy core system limitations to the immense pressures of tackling an exponential surge in social engineering scams with limited resources.

Connect with Hailey Windham