Swift has revealed new findings from a series of experiments that show how artificial intelligence (AI) and secure data collaboration could transform the fight against fraud in international payments.
The cooperative worked with 13 major financial institutions and several technology partners to test the impact of privacy-enhancing technologies (PETs) and federated learning. These tools were used to allow institutions to share fraud insights securely across borders, while still protecting customer data.
One use case allowed banks to verify suspicious accounts in real time through PETs, which could speed up the detection of complex global financial crime networks and prevent fraudulent transactions before they are executed. Another trial combined PETs with federated learning, an AI model that trains locally on each institution’s data without moving sensitive information. When tested on synthetic data from 10m artificial transactions, the collaborative model proved twice as effective at detecting known fraud compared to a model trained on a single dataset.
Swift head of AI Rachel Levi 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. The industry loses billions to fraud each year, but by enabling the secure sharing of intelligence across borders we’re paving the way for this figure to be significantly reduced, and allowing fraud to be stopped in a matter of minutes, not hours or days.”
The experiments included participation from ANZ, BNY and Intesa Sanpaolo, as well as Google Cloud. ANZ head of technology – payment services and digital assets David Buckthought said, “The rise in fraud and scams is a global issue impacting all financial institutions. ANZ is excited to be involved in an industry-wide response, proving the use of federated learning to enhance detection capabilities. This will provide banks with a stronger defence against fraudulent activity.”
BNY executive platform owner Isabel Schmidt said, “Security is paramount in cross-border payments. Using the latest technologies, this group has achieved results that show how these tools can be used to uplift the entire ecosystem and demonstrate the value of the Swift co-operative in bringing competitive organizations together behind a greater good, while driving standards in security and enhancing the experience of all stakeholders.”
Intesa Sanpaolo head of anti-fraud & customer protection centre Enrico Canna added, “Fraud in cross-border payments increases friction in the ecosystem and causes significant costs at an industry level. Intesa Sanpaolo is collaborating in these preliminary experiments led by Swift to demonstrate the positive impact of a synergistic approach supported by the latest technologies for making the ecosystem more secure and reliable.”
Swift confirmed that the next phase of trials will involve real transaction data to assess how the technologies perform in live fraud prevention scenarios. The cooperative has been expanding its AI research, with over 50 use cases currently in pilot or live operation. Financial crime cost the industry an estimated $485bn in 2023, and earlier this year Swift launched an AI-powered Payments Controls Service aimed at helping smaller financial institutions more effectively flag suspicious transactions.
Keep up with all the latest FinTech news here
Copyright © 2025 FinTech Global
