Thought SHAP made your fraud model explainable enough? Turns out there's a much bigger hole underneath. Title: What SHAP Can't Explain About Agentic AI Fraud URL: ❓ How does fraud detection spot "human-ness" in the first place? 💡 Typing dynamics, device switching, timing quirks: signals of human stress or deviation from a personal baseline. That assumption has underpinned fraud detection for a decade. ❓ What does SHAP actually give you? 💡 Ranked feature attribution over amount, timing, device, and velocity, explaining why a transaction looked suspicious in a way compliance analysts can audit and defend. ❓ What changes when the actor is an autonomous agent? 💡 No circadian rhythm, no panic-driven mistakes, superhuman consistency. The whole premise that "deviation from a human baseline signals fraud" simply stops applying. ❓ So what's the fix? 💡 The author argues for shifting from transaction-level scoring to "trajectory auditing", tracking an agent's decision path and tool calls, though no implemented solution exists yet. #FraudDetection# #ExplainableAI#

MCDONALD: "Just today, the fraud division signed data-sharing agreements with ten state agencies represented here across 6 states to formalize our shared commitment to the responsible sharing of publicly-available corporate registration and government benefits payment data for early fraud detection."

Anthropic is looking to build more billing, fraud detection and other financial infrastructure in-house, according to job postings. That's raising questions for what it could mean for Stripe (and helps to explain Stripe's recent OpenRouter deal):

Introducing Kled-FD 0.1, the world's best fraud detection and dataset cleaning pipeline. The first all in one system capable of detecting AI generated content, near duplicates, stolen and plagiarized media, screenshots, manipulated and spliced content, NSFW and explicit material, minors and age sensitive content, sensitive and harmful content, and coordinated behavioral fraud rings. Kled-FD 0.1 has been battle tested across 1.2 billion uploads on Kled's data marketplace and is actively running quality checks on over 5 million uploads per day across image, video, audio, and text. Public benchmarks will be released soon. This is the first real step toward making data quality enforcement a humanless process.

Stablecoin orchestration is... Banking Orchestration Liquidity Orchestration FX & Rate Locks Payout Orchestration KYB / KYC Orchestration Wallet Screening Sanctions & PEP Screening Transaction Monitoring Fraud Detection & Risk Scoring Travel Rule Compliance Cross-Chain Swaps Fee Profiles and more... All in one API via @iron. Learn more:

This Thursday on Novelty Search :: Bittensor SN54 Yanez @yanez__ai shows how #SN54# uses Bittensor miners to generate synthetic adversarial identity data for financial crime prevention, helping compliance teams stress-test sanctions screening, fraud detection, and KYC systems before criminals do. Join live via Bittensor Discord. Hosted by @const_reborn

We’ve started and are continuing to buy back over $1 million of $KLED in the last 48 hours. $KLED will ultimately become a fully viable reward currency for our data marketplace and human in the loop fraud detection tools we have built. As our contracts get bigger and bigger we will continue to support our token community accordingly and to our discretion.

Despite the fintech surge, trust remains a credit union advantage. Consumers still see CFIs as safer than digital banks, especially when it comes to data privacy and fraud protection. Double down on that perception. Use AgentFlow to operationalize safety: 1. Employ Decision AI for proactive fraud detection 2. Automate suspicious activity alerts via Conversational AILog and audit every action for compliance with full traceability Security and governance are embedded in the AgentFlow platform, from SOC 2 Type II compliance to VPC deployments and immutable audit logs.