Securing federated learning: a covert communication-based approach

• Main Authors: Xie, Yuan-Ai, Kang, Jiawen, Niyato, Dusit, Nguyen, Thi Thanh Van, Nguyen, Cong Luong, Liu, Zhixin, Yu, Han
• Other Authors: College of Computing and Data Science
• Format: Article
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Artificial intelligence; Federated learning
• Online Access: https://hdl.handle.net/10356/179061
• Institution: Nanyang Technological University

Federated Learning Networks (FLNs) have been envisaged as a promising paradigm to collaboratively train models among mobile devices without exposing their local privacy data. Due to the need for frequent model updates via wireless links, FLNs are vulnerable to various attacks (e.g., eavesdropping attacks, replay attacks, inference attacks, and jamming attacks). Balancing privacy protection with efficient distributed model training is a key challenge for FLNs. Existing countermeasures incur high computation costs and are only designed for specific attacks on FLNs. In this article, we bridge this gap by proposing the Covert Communication-based Federated Learning (CCFL) approach. Based on the emerging communication security technique of covert communication which hides the existence of wireless communication activities, CCFL can degrade attackers' capability of extracting useful information from the FLN training protocol, which is a fundamental step for most existing attacks, and thereby holistically enhances the privacy of FLNs. We experimentally evaluate CCFL extensively under real-world settings in which the FL latency is optimized under given security requirements. Numerical results demonstrate the significant effectiveness of the proposed approach in terms of both training efficiency and communication security.