Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap

TL;DR

This paper introduces a robust federated learning aggregation method using geometric median that effectively defends against Byzantine attacks, achieves zero optimality gap, and converges linearly under certain attack conditions.

Contribution

It proposes a novel aggregation technique with reduced communication and computation, ensuring zero optimality gap and linear convergence in Byzantine settings.

Findings

Achieves zero optimality gap under Byzantine attacks below half the users.

Reduces communication rounds and computational load compared to existing methods.

Numerical results confirm robustness and effectiveness of the proposed approach.

Abstract

In this paper, we propose a robust aggregation method for federated learning (FL) that can effectively tackle malicious Byzantine attacks. At each user, model parameter is firstly updated by multiple steps, which is adjustable over iterations, and then pushed to the aggregation center directly. This decreases the number of interactions between the aggregation center and users, allows each user to set training parameter in a flexible way, and reduces computation burden compared with existing works that need to combine multiple historical model parameters. At the aggregation center, geometric median is leveraged to combine the received model parameters from each user. Rigorous proof shows that zero optimality gap is achieved by our proposed method with linear convergence, as long as the fraction of Byzantine attackers is below half. Numerical results verify the effectiveness of our proposed method.