IMFL: An Incentive Mechanism for Federated Learning With Personalized Protection

Mengqian Li, Youliang Tian, Junpeng Zhang, Zhou Zhou, Dongmei Zhao, Jianfeng Ma

Abstract: Federated learning (FL) allows clients to keep local data sets and train collaboratively by uploading model gradients, which achieves the goal of learning from fragmented sensitive data. Although FL prevents clients’ data sets from being shared directly, local private information may be leaked through gradients. To mitigate this problem, we combine game theory to design an FL scheme (incentive mechanism for the FL) based on the incentive mechanism and differential privacy (DP). First, we explore three DP variants, all of which are resistant to deep leakage from gradients (DLG) but differ in their level of privacy protection. In addition, we perform the convergence analysis of the FL model based on DP. Then, with the assistance of game theory, we analyze the natural state of the server and clients in the FL process and formulate the utility function of both sides under the case of considering the attack. Finally, we establish the optimization problem as a Stackelberg game and solve for the optimal strategy of the server and clients by deriving the Nash equilibrium to achieve personalized protection. Theoretical proof demonstrates that both types of entities can achieve optimal actions by maximizing their utility functions upon reaching the Nash equilibrium. Besides, extensive experiments are conducted on real-world data sets to demonstrate that the IMFL is efficient and feasible.