Visa announced an enhanced version of A2A Protect on 09/02/2026, adding a unified fraud score designed to help financial institutions identify account-to-account fraud before money leaves customer accounts. The score is Visa’s first in-market integration of Featurespace technology since acquiring the company, and Visa says A2A Protect has increased fraud detection by 75% during the first six months of deployment.
The service provides real-time risk insights for account-to-account transactions through advanced AI and transfer learning. According to Visa, this approach gives banks access to global risk signals immediately, without waiting months for a model to learn from an institution’s own transaction history or for other banks to join a consortium.
Financial institutions can also opt in to incorporate network-level signals. Visa says those signals can highlight emerging scam hotspots and coordinated fraud activity across the payment ecosystem, providing information that may be difficult for an individual institution to detect alone and helping banks assess scams before authorization.
A2A Protect connects to financial institutions’ existing systems through a single API. Each alert includes a plain-language explanation of why a transaction was flagged, which Visa says is intended to help fraud teams respond without unnecessarily disrupting legitimate customers. The company also says the service has been shown to reduce more than 50% additional fraud and cut unnecessary fraud alerts by more than 40%.
The launch comes as account-to-account payments continue to expand globally. Citing Juniper Research’s Global Instant Payments Market Report from September 2025, Visa said A2A transactions are projected to exceed 5.8 trillion by 2028, representing a 160% increase from 2024.