Ping An Digital Bank has completed its use case in the second cohort of the Hong Kong Monetary Authority’s (HKMA) GenAI Sandbox.

According to the bank, its fraud platform detected deepfakes with over 96% accuracy in sandbox tests.

The HKMA runs the sandbox together with Cyberport. It gives banks a space to test and explore new financial tools.

The bank built the platform, known as the Anti-Fraud Strategy Platform, with OneConnect Financial Technology.

It draws on in-house technology from both Ping An Group and OneConnect.

The system adds AI facial recognition to the bank’s identity checks. This allows it to review user selfies in real time and flag faces that may be forged or altered.

The bank said this helps its teams monitor and prevent fraud at an early stage.

During the sandbox, the project focused on how well the platform could detect deepfakes. The bank also explored the potential of an “AI vs AI” defence strategy.

“We believe the experience gained will help strengthen the industry’s ability to counter deepfake fraud, and build a more robust defence mechanism,”

said Ronald Iu, Chief Executive at Ping An Digital Bank.

Iu noted that the bank received guidance from the HKMA during the process. It also shared its experience with industry peers.

Ping An Digital Bank plans to increase its investment in AI. The bank also intends to apply AI more widely in its daily work, including risk control and new products.

Featured image: Edited by Fintech News Hong Kong, based on image by Magnific.