Robust Federated Learning via Over-The-Air Computation

TL;DR

This paper enhances the robustness of over-the-air federated learning against Byzantine attacks by introducing a group-based transmission and robust aggregation framework, ensuring reliable model updates despite malicious client behavior.

Contribution

It proposes a novel group-based transmission scheme and robust aggregation method to defend against Byzantine attacks in over-the-air federated learning.

Findings

The proposed method effectively mitigates Byzantine attacks.

Numerical simulations demonstrate improved robustness.

The convergence of the algorithm is theoretically analyzed.

Abstract

This paper investigates the robustness of over-the-air federated learning to Byzantine attacks. The simple averaging of the model updates via over-the-air computation makes the learning task vulnerable to random or intended modifications of the local model updates of some malicious clients. We propose a robust transmission and aggregation framework to such attacks while preserving the benefits of over-the-air computation for federated learning. For the proposed robust federated learning, the participating clients are randomly divided into groups and a transmission time slot is allocated to each group. The parameter server aggregates the results of the different groups using a robust aggregation technique and conveys the result to the clients for another training round. We also analyze the convergence of the proposed algorithm. Numerical simulations confirm the robustness of the proposed approach to Byzantine attacks.