FAMOS: Robust Privacy-Preserving Authentication on Payment Apps via Federated Multi-Modal Contrastive Learning
Yifeng Cai, Ziqi Zhang, Jiaping Gui, Bingyan Liu, Xiaoke Zhao, Ding Li
33rd USENIX Security Symposium · Day 1 · USENIX Security '24
In an era where digital payment applications have become ubiquitous, securing transactions against unauthorized access is paramount. The talk "FAMOS: Robust Privacy-Preserving Authentication on Payment Apps via Federated Multi-Modal Contrastive Learning" by Yifeng Cai and colleagues introduces a novel solution to this critical challenge. This research directly addresses significant limitations in existing authentication methods for payment apps, which are often vulnerable to device compromise or privacy breaches.
AI review
FAMOS presents a robust and privacy-preserving authentication framework for payment applications, addressing critical limitations in existing behavioral biometrics. By intelligently fusing multimodal sensor data, employing privacy-centric contrastive learning, and leveraging federated learning, it delivers significant performance improvements while navigating real-world noise and stringent privacy regulations. This is a well-executed defensive innovation for a high-stakes environment.