(16 October 2024 – Global) Swift is launching a new AI-driven anomaly detection service designed to help banks identify and prevent potential financial crime more proactively.
This service, set to be available in January 2025, follows a successful pilot program involving financial institutions in Europe, North America, Asia, and the Middle East.
The AI-based feature enhances Swift’s existing Payment Controls Service, widely used by small and medium-sized financial institutions. By leveraging pseudonymised data from billions of transactions processed on Swift’s messaging network annually, the service will detect and flag suspicious activities, enabling banks to respond in real-time.
Jerome Piens, Swift’s chief product officer, explains: “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.”
Since February, Swift has collaborated with its member banks to investigate how federated learning and privacy-enhancing technologies could allow market participants to share critical information without disclosing proprietary data. Several fraud detection use cases have been developed and will soon undergo testing in a sandbox environment.
Olivier Nautet, head of cybersecurity at BNP Paribas, emphasised the importance of this collaborative effort: “Collaboration across the banking sector is crucial to enhancing fraud detection, and by sharing data and leveraging AI, we empower ourselves to stay ahead. At BNP Paribas, we are fully committed to supporting Swift’s innovative initiative in that regard, as it marks a key step forward in protecting the integrity of our financial ecosystem.”