Swift is rolling out a new AI-based fraud defence system to help banks proactively detect and defend against potential financial crime during cross-border payments.

The service, which will be available from January 2025, is the result of Swift’s collaboration with over 11,500 banks and financial institutions, including BNP Paribas and Standard Bank, to test how AI can solve cross-industry challenges.

It builds on Swift’s existing Payment Controls Service, which is used by many small and medium-sized financial institutions, by drawing on pseudonymised data from the billions of transactions conducted through the Swift network each year to identify and flag suspicious transactions so that action can be taken in real-time.

The defence system follows a trial of two pilot projects conducted by Swift in May this year. At the time, the company said the ability for AI to facilitate confidential data sharing could be a “game-changer” for the industry.

Swift said it has been working with global financial institutions since February to explore how federated learning, a machine learning technique that allows multiple entities to train a model together while keeping their data decentralised, combined with privacy-enhancing technologies, could enable market participants to share information without revealing their proprietary data.
The group has so far developed a number of fraud detection use cases which are set to be tested in a sandbox environment.

“Bad actors are using increasingly sophisticated tactics to commit financial crime, and the global financial industry needs to raise its defences higher to ensure their customers can continue to transact globally with confidence,” said Jerome Piens, chief product officer at Swift. “Swift has a long track record of supporting our community by staying one step ahead to maintain the security and resilience that our network is known for - and now we’re doing so again by harnessing the latest technology.”

---