Tackling Byzantine Clients in Federated Learning

arXiv:2402.12780v1 Announce Type: new
Abstract: The possibility of adversarial (a.k.a., {\em Byzantine}) clients makes federated learning (FL) prone to arbitrary manipulation. The natural approach to robustify FL against adversarial clients is to replace the simple averaging operation at the server in the standard $\mathsf{FedAvg}$ algorithm by a \emph{robust averaging rule}. While a significant amount of work has been devoted to studying the convergence of federated {\em robust averaging} (which we denote by $\mathsf{FedRo}$), prior work has largely ignored the impact …

abstract adversarial algorithm arxiv cs.lg federated learning manipulation natural possibility robust server simple standard type