Mean Aggregator Is More Robust Than Robust Aggregators Under Label Poisoning Attacks

arXiv:2404.13647v1 Announce Type: new
Abstract: Robustness to malicious attacks is of paramount importance for distributed learning. Existing works often consider the classical Byzantine attacks model, which assumes that some workers can send arbitrarily malicious messages to the server and disturb the aggregation steps of the distributed learning process. To defend against such worst-case Byzantine attacks, various robust aggregators have been proven effective and much superior to the often-used mean aggregator. In this paper, we show that robust aggregators are too …

abstract aggregation arxiv attacks cs.lg distributed distributed learning importance mean messages poisoning attacks process robust robustness server type workers