The Swift international interbank payment system has announced two artificial intelligence (AI)-based experiments in collaboration with its member banks, to explore how the technology could assist in combatting cross-border payments fraud and save the industry billions in fraud-related costs.

In the first pilot, Swift is enhancing its existing payment controls service – which helps financial institutions detect anomalies that could be indicative of fraud – by using an AI model that will create a more nuanced and accurate picture of potential fraud activity, using historical patterns of activity on the Swift network.

Swift will work with payment controls customers to refine the enhancement, and the test will use the customers’ own live traffic data – giving the findings real-world applicability.

In a separate experiment, Swift has convened 10 leading financial institutions to test how it can use advanced AI technology to analyse anonymously-shared data from different sources in a way that will strengthen the global financial ecosystem.

AI’s capability for confidential data sharing could be a game-changer for the industry. The tests could lead to the wider use of information sharing in fraud detection, building on its success in assessing cyber security threats.

The group, which includes leading banks from around the world, among them, BNY Mellon, Deutsche Bank, DNB, HSBC, Intesa Sanpaolo and Standard Bank, will test the use of secure data collaboration and federated learning technologies.

It will leverage a secure infrastructure that will enable financial institutions to exchange relevant information with strong privacy-preserving controls. Swift’s AI anomaly detection model will then be able to gather insights and identify potential fraud patterns from a much richer dataset.

In 2023 alone, fraud, according to Swift, cost the financial industry US$485 billion. AI has a strong role to play in reducing these costs; and, at the same time, tackling the issue will significantly help the industry achieve the G20’s goal of increasing the speed of cross-border payments.

Swift, it says, is uniquely placed to spearhead industry efforts against fraud due to its role as a trusted entity at the heart of the financial ecosystem, and because of the breadth and reach of the data that travels across its network.

The payment service, it points out, has built an AI governance framework, in collaboration with its community, to ensure that accuracy, explainability, fairness, auditability, security and privacy are integral to every aspect of its AI applications. These pilots are rooted in the responsible use of AI and are aligned with emerging global standards, such as ISO 42001, the NIST AI Risk Management Framework and the EU AI Act.

“AI has great potential to significantly reduce fraud in the financial industry,” states Tom Zschach, Swift’s chief innovation officer. “That’s an incredibly exciting prospect, but one that will require strong collaboration. Swift has a unique ability to bring financial organisations together to harness the benefits of AI in the interests of the industry, and we’re excited by the potential of both of these pilots to help further strengthen the cross-border payments ecosystem.”