Skip to content

Rapid Advancements in Artificial Intelligence Design Pave Way for Banks to Swiftly Prevent Fraud Across Borders by Embracing Collaboration Among Institutions

AI-driven research spearheaded by Swift is unveiling the possible influence of artificial intelligence and secure cross-border data sharing in decreasing fraud in global transactions.

Cross-border collaboration encouraged among banks to accelerate fraud prevention using advanced AI...
Cross-border collaboration encouraged among banks to accelerate fraud prevention using advanced AI technology proposed by Swift.

Rapid Advancements in Artificial Intelligence Design Pave Way for Banks to Swiftly Prevent Fraud Across Borders by Embracing Collaboration Among Institutions

Swift Leads Industry-Wide Experiments to Reduce Fraud in Cross-Border Payments

In a bid to combat the staggering financial loss caused by fraud, Swift is leading a collaborative effort involving 13 global financial institutions. The aim is to significantly reduce the billions lost annually by enabling the secure sharing of intelligence across borders.

Swift's technology partners in this endeavour include ANZ, BNY, Intesa Sanpaolo, and Google Cloud. The experiments are designed to provide banks with a stronger defence against fraudulent activity, demonstrating Swift's role as a trusted cooperative at the heart of global finance.

David Buckthought, Head of Technology - Payment Services and Digital Assets at ANZ, expressed his excitement about the industry-wide response to fraud, highlighting its negative impact on cross-border payments. Enrico Canna, Head of Anti-Fraud & Customer Protection Centre at Intesa Sanpaolo, echoed similar sentiments, emphasising the importance of security in cross-border payments.

Isabel Schmidt, Executive Platform Owner at BNY, also emphasised the importance of security, particularly in the context of the AI-enhanced Payments Controls Service launched by Swift. This service is designed to help small and medium-sized financial institutions more accurately flag suspicious transactions.

The experiments involve the use of privacy-enhancing technologies (PETs) to securely share fraud insights. One use case enables participants to verify intelligence on suspicious accounts in real-time, while another combines PETs and federated learning to identify anomalous transactions. The latter was twice as effective in identifying known frauds as a model trained on a single institution's dataset.

Swift currently has over 50 use cases across proof of concept, pilots, and live usage. The experiments are part of Swift's ongoing efforts to enhance the speed, efficiency, and security of cross-border transactions. Swift intends to expand participation and launch a second phase of tests using real transaction data to demonstrate the technologies' impact on real-world fraud.

The experiments aim to allow fraud to be stopped in a matter of minutes, not hours or days. With financial crime estimated to have cost the industry USD 485bn in 2023 alone, these efforts could potentially make a significant dent in this figure.

While the search results do not specify the additional financial institutions involved in the SWIFT-led experiments to reduce fraud in international payments, it is clear that this collaborative approach, supported by the latest technologies, could pave the way for a more secure future in global finance.

Read also:

Latest