Banking co-operative Swift is set to launch an AI-powered anomaly detection service designed to assist banks in proactively identifying and combating potential financial crime.
Scheduled for release in January 2025, this new service follows a successful pilot program involving financial institutions across Europe, North America, Asia, and the Middle East. It enhances Swift’s existing Payment Controls Service, widely utilized by small and medium-sized financial institutions, by utilizing pseudonymized data from billions of transactions processed through the messaging network each year. This capability is intended to identify and flag suspicious transactions for real-time action.
Jerome Piens, chief product officer at Swift, stated, “Bad actors are using increasingly sophisticated tactics to commit financial crime, and the global financial industry needs to raise its defenses higher to ensure their customers can continue to transact globally with confidence.”
Since February, Swift has collaborated with member banks to investigate how federated learning, along with privacy-enhancing technologies, can facilitate the sharing of information without disclosing proprietary data. Several fraud detection use cases have been developed and are set to be tested in a sandbox environment.
Olivier Nautet, head of cybersecurity at BNP Paribas, emphasized the importance of collaboration in the banking sector for improving fraud detection. He remarked, "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, as it represents a significant step forward in protecting the integrity of our financial ecosystem."
For insights into the challenges and opportunities that artificial intelligence presents to the banking sector, consider attending Finextra’s first NextGenAI conference on November 26, 2024. Register your interest here.