Swift AI launches AI-powered cross-border fraud detection

By Vriti Gothi

Swift AI has collaborated with 13 leading international banks, has demonstrated a breakthrough in real-time fraud detection through pioneering experiments leveraging AI and secure cross-border data collaboration. The trials, involving ten million synthetic transactions, show that coordinated, technology-driven approaches could significantly strengthen global financial crime prevention.

The experiments deployed advanced privacy-enhancing technologies (PETs) to enable institutions to share transaction intelligence while maintaining strict end-to-end privacy and security. In one use case, PETs allowed participants to validate suspicious accounts in real time, accelerating the identification of complex international fraud networks and preventing fraudulent transactions before they are executed.

In a second, more advanced scenario, federated learning, an AI methodology that trains models locally at each institution without exposing customer data, was combined with PETs to detect anomalous transactions. When trained on the synthetic dataset, this collaborative AI model doubled the detection effectiveness compared with models trained in isolation at individual banks.

Rachel Levi, Head of AI at Swift, said, “These experiments demonstrate the convening power of Swift as a trusted cooperative at the heart of global finance. A united, industry-wide fraud defence will always be stronger than one put up by a single institution acting alone. By securely sharing intelligence across borders, we can dramatically reduce the billions lost to fraud each year, stopping suspicious activity in minutes rather than hours or days.”

Following these successful trials, Swift plans to broaden participation and launch a second phase of experiments using real transaction data, aiming to validate the practical impact of these technologies in live environments.

Swift has long been at the forefront of financial industry innovation, combining advanced technology with cooperative models to enhance the speed, efficiency, and security of cross-border payments. Currently, Swift is exploring AI applications across more than 50 use cases spanning proofs of concept, pilot projects, and live deployment. Earlier this year, the organisation introduced an AI-enhanced Payments Controls Service, empowering small and medium-sized financial institutions to flag suspicious transactions in real time.

Participants in the trials included ANZ, BNY, and Intesa Sanpaolo, alongside technology partners such as Google Cloud.