Swift and Google Cloud team up to fight fraud with AI innovation

Swift is a global financial messaging service provider. google cloud Develop innovative anti-fraud technology.

This initiative was developed in partnership with Rhino Health. cap geminiaims to address the limitations of traditional fraud detection methods, which are often difficult to keep up with sophisticated criminal tactics that span multiple agencies and countries.

The partnership leverages advanced AI and federated learning technologies in combination with Privacy Enhancing Technology (PET) and Trusted Execution Environment (TEE).

This enables collaborative intelligence without compromising the privacy or security of sensitive financial data.

Federated learning allows participating institutions to train AI models on their own data and share only the learning, not the data itself, with a central server managed by Swift.

This approach enhances fraud detection while ensuring data confidentiality.

quickly plans to launch a sandbox environment in the first half of 2025 with Google Cloud as a strategic partner.

The sandbox will enable 12 global financial institutions to create prototypes that use Swift’s anomaly detection models as a foundation and learn from historical fraud data.

The initiative builds on Swift’s existing Payment Controls Service and follows a successful pilot program involving institutions in Europe, North America, Asia, and the Middle East.

This collaborative approach has several benefits. By sharing insights, agencies can identify complex fraud schemes that may go undetected by individual organizations.

Improved models result in more accurate threat identification and fewer false alarms, thereby reducing disruption to legitimate activities.

Sharing knowledge allows us to respond quickly to new fraud trends and ensures that our systems remain effective against evolving threats.

The more institutions that participate, the more effective the system becomes, creating a powerful network effect that strengthens fraud prevention for all involved.

This project is focused on data privacy and security and utilizes privacy-enhancing technologies and confidential computing techniques to protect sensitive information.

“This study will help the community discover whether federated learning technology can help financial institutions stay one step ahead of bad actors through fraud label sharing, and in turn provide customers with an enhanced cross-border payments experience. It will help you verify.”

Rachel Levi, Head of Artificial Intelligence at Swift, said:

andrea gallego
“Our collaboration with Swift demonstrates the transformative potential of federated learning and confidential computing.
By enabling secure collaboration and knowledge sharing without compromising data privacy, we are fostering a more secure and resilient financial ecosystem for everyone. ”