Paper accepted in IEEE Transactions on Information Forensics and Security 2020

Ming Ding had a paper accepted in IEEE Transactions on Information Forensics and Security (TIFS) 2020. In this paper, to effectively prevent information leakage in federated learning, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noises are added to the parameters at the clients’ side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noises. Then we develop a theoretical convergence bound of the loss function of the trained FL model in the NbAFL.

• Kang Wei, Jun Li, Ming Ding, Chuan Ma, Howard H. Yang, Farokhi Farhad, Shi Jin, Tony Q. S. Quek, and H. Vincent Poor, “Federated Learning with Differential Privacy: Algorithms and Performance Analysis,” to appear in IEEE Transactions on Information Forensics and Security [https://arxiv.org/abs/1911.00222]