Can I read Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering on EtoBox?

Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering by Xu, Jian; Huang, Shao-Lun; Song, Linqi; Lan, Tian is a scholarly article available to read on EtoBox.

What is Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering about?

Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e.g., by computing validation error rate) or leverages statistic-based methods (e.g. median and Krum) to identify and remove malicious gradients from Byzantine clients. In this paper, we remark that auxiliary data may not always be available in practice and focus on the statistic-based approach. However, recent work on model poisoning attacks has shown that well-crafted attacks can circumvent most of median- and distance-based statistical defense methods, making malicious gradients indistinguishable from honest ones. To tackle this challenge, we show that the element-wise sign of gradient vector can provide valuable insight in detecting model poisoning attacks. Based on our theoretical analysis of the \textit{Little is Enough} attack, we propose a novel approach called \textit{SignGuard} to enable Byzantine-robust federated learning through collaborative malicious gradient filtering. More precisely, the received gradients a

Author

Xu, Jian; Huang, Shao-Lun; Song, Linqi; Lan, Tian

Published

2021

Language

EN