Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting

Yuchen Liu*

Chen Chen

Lingjuan Lyu

Fangzhao Wu*

Sai Wu*

Gang Chen*

* External authors

ICML 2023

2023

Abstract

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to the central server to destroy the convergence and performance of the global model. A wealth of defenses have been proposed to defend against Byzantine attacks. However, Byzantine clients can still circumvent defense when the data is non-identically and independently distributed (non-IID). In this paper, we first reveal the root causes of current robust AGgregation Rule (AGR) performance degradation in non-IID settings: the curse of dimensionality and gradient heterogeneity. In order to address this issue, we propose GAS, a gradient splitting based approach that can successfully adapt existing robust AGRs to ensure Byzantine robustness under non-IID settings. We also provide a detailed convergence analysis when the existing robust AGRs are adapted to GAS. Experiments on various real-world datasets verify the efficacy of our proposed GAS.