←
Fraud.net13,650 posts
Fraud.net avatar

Fraud.net

@Fraud_net

AI-powered platform that empowers enterprises to manage risk and streamline compliance, dramatically reducing fraud & false positives. Request a demo today!

◷ Joined October 2009▧ 3,287 Photos and videos
Fraud.net avatar
Fraud.net@Fraud_net·Jun 3

AI-generated fraud doesn't announce itself in a single transaction. It builds, across entities, channels, and time, until the damage is done. In last week's webinar, we brought together risk leaders from Bankingly, epay/Skylight (Euronet), and Brains Capital to talk about what rule-based detection misses, what behavioral signals catch earlier, and what the shift to AI agents actually requires from your governance program. Watch the full session now: buff.ly/ksV6jHH
 #entityrisk #merchantrisk #entityriskintelligence #ai #generativeai #aigeneratedfraud #fraudrisk #fraudprevention #frauddetection #payments #banking #fightfraud

Post attachment
Fraud.net avatar
Fraud.net@Fraud_net·Nov 11

Our CEO Whitney Anderson wrote Chapter 3 of VITAL4’s AUSTRAC Financial Crime Solution Series. Picking up where screening leaves off, he explains why fraud like account takeover and mule activity hides in behaviour across many small signals, and how bringing all of them together under one view of each customer lets your team see the pattern instead of chasing individual alerts. We’re glad to be contributing alongside @VITAL4 and @Veresure. buff.ly/xXwxmC8 #AUSTRAC #AML #FraudDetection #TransactionMonitoring

1:01
Fraud.net avatar
Fraud.net@Fraud_net·Nov 3

Some of your scam gaps may not need a new tool at all. If device data sits with your authentication team and payment monitoring can't query it, the data already exists. The join needs to be built, and someone needs to own the request. Sort your gap list by the kind of work each gap needs. Data never collected is a roadmap item; data collected but sitting in separate systems is work you can schedule this quarter. Get the guide: buff.ly/MYRkUqQ #ScamPrevention #FraudPrevention #FinancialCrime #RiskManagement

Post attachment
Fraud.net avatar
Fraud.net@Fraud_net·Oct 26

For 2025, the Consumer Federation of America compared $20.8 billion in US consumer fraud losses reported to the FTC with an implied $148.2 billion in actual losses. Your own case records have the same blind spot: a scam that was never reported never becomes a case. Link analysis shows how the cases you did confirm connect to each other, and those connections can point to activity that never reached your caseload. See how in our guide, "Can You See the Network Behind Your Scam Losses?": buff.ly/MYRkUqQ #ScamPrevention #FraudPrevention #LinkAnalysis #FinancialCrime

Post attachment
Fraud.net avatar
Fraud.net@Fraud_net·Oct 22

An analyst spots one BIN pattern by hand, then has to go looking for it again tomorrow, and the day after that. Card testing spreads across merchants faster than any manual process can track, and rules tuned to catch one merchant at a time miss the pattern spreading across hundreds. Get the full session here to see what real-time, BIN-level Card Testing Detection looks like instead, catching coordinated attacks automatically instead of one query at a time: buff.ly/ks0XO2x #CardTesting #FraudPrevention #MerchantRisk #PaymentsFraud

Post attachment
Fraud.net avatar
Fraud.net@Fraud_net·Oct 22

What percentage of your confirmed scam cases were linked to another case? Every case reaches your team as one row, with no link to the others in the queue. Meanwhile, the criminal network behind it keeps its accounts, identities and devices, and can reuse them against you. The guide gives you three checks for each of five layers, so you can see where your data can answer that question and where it can't. Get the guide: buff.ly/MYRkUqQ #ScamPrevention #FraudPrevention #LinkAnalysis #MuleAccounts

Post attachment
Fraud.net avatar
Fraud.net@Fraud_net·Oct 21

Your scam loss figure is accurate. It also describes only the last step of a longer chain. A reported case is one payment, one beneficiary account and one row in your data. Beneath it sit five layers: mule account intake, identity assembly, device and session reuse, money movement and cash-out, and network coordination. Our new guide, "Can You See the Network Behind Your Scam Losses?", walks through each layer with three checks you can run against your own data. Get the guide: buff.ly/MYRkUqQ #ScamPrevention #FraudPrevention #MuleAccounts #FinancialCrime

Post attachment