A Huber Loss Minimization Approach to Byzantine Robust Federated Learning

arXiv:2308.12581v2 Announce Type: replace
Abstract: Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and identically distributed (i.i.d) assumption, our approach has several advantages compared to existing methods. Firstly, it has optimal dependence on $\epsilon$, which stands for the ratio of attacked clients. Secondly, our approach does not need precise knowledge of $\epsilon$. Thirdly, it allows different clients to have …

abstract advantages adversarial adversarial attacks analysis arxiv attacks cs.ai cs.lg distributed federated learning independent learning systems loss novel robust systems type