Coded Robust Aggregation for Distributed Learning under Byzantine Attacks

TL;DR

This paper introduces a coded robust aggregation method for distributed learning that improves resilience against Byzantine attacks by making honest gradients more similar, thus enhancing robustness and convergence.

Contribution

The paper proposes CRA-DL, a novel distributed learning approach using coded gradients to improve robustness against Byzantine attacks, with theoretical analysis and empirical validation.

Findings

CRA-DL enhances robustness against Byzantine attacks.

Coded gradients are closer, improving aggregation stability.

CRA-DL outperforms existing methods in experiments.

Abstract

In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have been proposed at the central server to mitigate the impact of Byzantine attacks. However, current DL methods apply RBA rules for the local gradients from the honest devices and the disruptive information from Byzantine devices, and the learning performance degrades significantly when the local gradients of different devices vary considerably from each other. To overcome this limitation, we propose a new DL method to cope with Byzantine attacks based on coded robust aggregation (CRA-DL). Before training begins, the training data are allocated to the devices redundantly. During training, in each iteration, the honest devices transmit coded gradients to the server computed from the allocated training data, and the server then aggregates the information received from both honest and Byzantine devices using RBA rules. In this way, the global gradient can be approximately recovered at the server to update the global model. Compared with current DL methods applying RBA rules, the improvement of CRA-DL is attributed to the fact that the coded gradients sent by the honest devices are closer to each other. This closeness enhances the robustness of the aggregation against Byzantine attacks, since Byzantine messages tend to be significantly different from those of honest devices in this case. We theoretically analyze the convergence performance of CRA-DL. Finally, we present numerical results to verify the superiority of the proposed method over existing baselines, showing its enhanced learning performance under Byzantine attacks.