Securing federated learning: a covert communication-based approach

• المؤلفون الرئيسيون: Xie, Yuan-Ai, Kang, Jiawen, Niyato, Dusit, Nguyen, Thi Thanh Van, Nguyen, Cong Luong, Liu, Zhixin, Yu, Han
• مؤلفون آخرون: College of Computing and Data Science
• التنسيق: مقال
• اللغة: English
• منشور في: 2024
• الموضوعات: Computer and Information Science; Artificial intelligence; Federated learning
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/179061
• المؤسسة: 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 at...