Byzantine-Resilient Federated Machine Learning via Over-the-Air Computation

Abstract

Federated learning (FL) is recognized as a key enabling technology to provide intelligent services for future wireless networks and industrial systems with delay and privacy guarantees. However, the performance of wireless FL can be significantly degraded by Byzantine attack, such as data poisoning attack, model poisoning attack and free-riding attack. To design the Byzantine-resilient FL paradigm in wireless networks with limited radio resources, we propose a novel communication-efficient robust model aggregation scheme via over-the-air computation (AirComp). This is achieved by applying the Weiszfeld algorithm to obtain the smoothed geometric median aggregation against Byzantine attack. The additive structure of the Weiszfeld algorithm is further leveraged to match the signal superposition property of multiple-access channels via AirComp, thereby expediting the communication-efficient secure aggregation process of FL. Numerical results demonstrate the robustness against Byzantine devices and good learning performance of the proposed approach.

arXiv commentAccepted by ICC workshop

References in corpus (7)

• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning for Mobile Keyboard Prediction
• Robust Aggregation for Federated Learning
• Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
• Geometric median and robust estimation in Banach spaces
• On Analog Gradient Descent Learning over Multiple Access Fading Channels