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 (12)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
• Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization
• Differentially Private Federated Learning: A Client Level Perspective
• Federated Learning with Bayesian Differential Privacy
• On Analog Gradient Descent Learning over Multiple Access Fading Channels
• Differential Privacy-enabled Federated Learning for Sensitive Health Data
• Federated Learning with Differential Privacy: Algorithms and Performance Analysis
• Federated Learning via Over-the-Air Computation
• Energy-Efficient Radio Resource Allocation for Federated Edge Learning
• Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)
• Linear Queries Estimation with Local Differential Privacy

Cited by in corpus (10)

• A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysis
• Transparent Contribution Evaluation for Secure Federated Learning on Blockchain
• LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy
• A Theoretical Perspective on Differentially Private Federated Multi-task Learning
• Wireless for Machine Learning
• Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control
• Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communication
• Machine Learning Systems for Intelligent Services in the IoT: A Survey
• Decentralized Wireless Federated Learning with Differential Privacy
• Strong Privacy and Utility Guarantee: Over-the-Air Statistical Estimation