Visa Launches Enhanced A2A Protect with Unified Fraud Score to Combat Rising Account-to-Account Fraud

Visa boosts A2A fraud prevention tech

This content has been selected, created and edited by the Finextra editorial team based upon its relevance and interest to our community. A2A transactions are projected to surpass 5.8 trillion by 2028, a 160% increase from 2024, making them increasingly attractive to fraudsters. Visa's A2A Protect uses AI and sophisticated transfer learning to give banks immediate access to critical global risk insights on transactions, without waiting months for models to develop intelligence from a bank's own transaction data. A2A Protect has been shown to reduce over 50% more fraud and help reduce over 40% in unnecessary fraud alerts, says Visa. The new, improved, version takes advantage of technology from British AI-powered financial fraud fighting outfit Featurespace, which Visa acquired in 2024. It introduces a new unified fraud score, giving financial institutions faster, clearer signals to detect more fraud while reducing unnecessary alerts. James Mirfin, head, risk and security solutions, Visa, says: "A2A Protect combines Visa's network expertise with Featurespace's technology to deliver a powerful new layer of protection that helps financial institutions detect more fraud, earlier." Featurespace is not Visa's only substantial security-related acquisition of recent times: last month it agreed to buy Israeli behavioural biometrics company BioCatch for $2.4 billion in cash.

Visa Debuts Enhanced Version of A2A Fraud Prevention Tool | PYMNTS.com

The payments giant on Tuesday (Sept. 1) debuted an enhanced version of its A2A project, designed to offer real-time risk insights that help banks stop A2A fraud before funds leave customer accounts. "Fraudsters move fast across payment types, and financial institutions need risk insights just as quickly, without slowing down legitimate payments," James Mirfin, head of risk and security solutions at Visa, said in a news release. "A2A Protect combines Visa's network expertise with Featurespace's technology to deliver a powerful new layer of protection that helps financial institutions detect more fraud, earlier." According to the release, A2A Protect uses AI and transfer learning to provide immediate risk insights for account-to-account transactions, bypassing the need for local model training or consortium setup. Banks that opt into network-level intelligence sharing can integrate ecosystem-wide signals to identify coordinated fraud and emerging scam hotspots, the release said. "This gives financial institutions a more complete and early view of risk, helping to identify scams before authorization," Visa added. "In fact, Visa A2A Protect has been shown to increase fraud detection by 75% in the first six months of deployment." Visa noted that the expanded A2A Protection comes as global A2A transactions are projected to exceed 5.8 trillion by 2028, a 160% increase from 2024. Visa recently beefed up its fraud prevention capabilities with its $2.4 billion acquisition of Israeli company BioCatch. As covered here last month, BioCatch employs AI and machine learning-based solutions "that analyze thousands of application, behavioral, device, and network signals like keystrokes and device handling to separate legitimate users from fraudsters." In other fraud-prevention news, the recent PYMNTS Intelligence/Plaid report "Payment Protection: Why Firms Still Aren't Real-Time Ready" shows that while businesses want to transmit money in seconds, their defenses often require much more time to catch up. Of the companies surveyed, 65% said they plan to bolster identity verification, while another 59% aim to expand secure bank connectivity and AI-based fraud detection. "The findings show a clear gap between the tools firms own and the results they achieve. Nearly every firm surveyed has secure bank connectivity," PYMNTS wrote. "Many also use real-time identity checks and several layers of fraud screening. Yet these tools often cover only selected payments or limited parts of the payment process. That leaves businesses exposed when funds move faster than their teams can review them."

Visa Launches Enhanced Version of A2a Protect with Unified Fraud Score

Visa announced an enhanced version of A2A Protect, delivering real-time risk insights that help banks stop account-to-account fraud before money leaves customer accounts. The expanded solution introduces a new unified fraud score?Visa?s first in-market integration of Featurespace technology?giving financial institutions faster, clearer signals to detect more fraud while reducing unnecessary alerts. A2A Protect leverages advanced AI and sophisticated transfer learning and gives banks immediate access to critical global risk insights on A2A transactions, without waiting months for models to develop intelligence from a bank?s own transaction data, and without having to wait for other banks to join a consortium, delivering results and value from day one. Banks that opt in can incorporate additional network-level signals to enhance detection of emerging threats operating across the ecosystem. For financial institutions that opt into network level intelligence sharing, A2A Protect highlights emerging scam hotspots and coordinated fraud activity ? insights that may be difficult for individual financial institutions to detect alone, and that help the wider ecosystem respond faster to new threats. This gives financial institutions a more complete and early view of risk, helping to identify scams before authorization. Visa A2A Protect has been shown to increase fraud detection by 75% in the first six months of deployment. A2A Protect integrates with financial institutions? current systems through a single API, reducing implementation time and complexity. Each alert includes a plain language explanation of why a transaction was flagged, helping fraud teams act quickly and confidently without disrupting genuine customers.