Wireless Federated Learning with Local Differential Privacy

Abstract

In this paper, we study the problem of federated learning (FL) over a wireless channel, modeled by a Gaussian multiple access channel (MAC), subject to local differential privacy (LDP) constraints. We show that the superposition nature of the wireless channel provides a dual benefit of bandwidth efficient gradient aggregation, in conjunction with strong LDP guarantees for the users. We propose a private wireless gradient aggregation scheme, which shows that when aggregating gradients from $K$ users, the privacy leakage per user scales as $\mathcal{O}\left(\frac{1}{\sqrt{K}}\right)$ compared to orthogonal transmission in which the privacy leakage scales as a constant. We also present analysis for the convergence rate of the proposed private FL aggregation algorithm and study the tradeoffs between wireless resources, convergence, and privacy.

References in corpus (4)

• Differential Privacy-enabled Federated Learning for Sensitive Health Data
• Federated Learning with Differential Privacy: Algorithms and Performance Analysis
• Energy-Efficient Radio Resource Allocation for Federated Edge Learning
• Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)