Swift, the Belgium-based financial messaging cooperative, has carried out experiments demonstrating how AI and secure cross-border data collaboration could help reduce fraud in international payments.
In partnership with 13 global financial institutions, the tests applied privacy-enhancing technologies (PETs) to allow participants to exchange fraud-related insights securely across jurisdictions.
In one case, PETs enabled the real-time verification of intelligence on suspicious accounts, potentially shortening the time needed to identify international financial crime networks and preventing fraudulent payments from being executed.
Another case combined PETs with federated learning, an AI technique that trains models locally at each institution without sharing customer data.
Using synthetic data from ten million artificial transactions, the model was twice as effective in detecting known frauds compared with one trained on a single institution’s data.
Rachel Levi, Head of AI at Swift, 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.”
Swift plans to expand participation before moving to a second phase of trials using real transaction data to assess the impact of the technologies in live environments.
The cooperative has been exploring AI’s role in financial services, with more than 50 use cases ranging from proofs of concept to live applications.
Financial crime is estimated to have cost the sector US$485 billion in 2023.
Earlier this year, Swift introduced an AI-enhanced Payments Controls Service to support smaller financial institutions in identifying potentially fraudulent activity in real time.
Institutions involved in the experiments included ANZ, BNY and Intesa Sanpaolo, alongside technology partners such as Google Cloud.
Featured image credit: Edited by Fintech News Switzerland, based on image by New Africa via Freepik
