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 unequal data sizes. We then broaden our analysis to include non-i.i.d data, such that clients have slightly different distributions.

翻译：联邦学习系统容易受到对抗性攻击。为应对这一问题，我们引入了一种基于Huber损失最小化的新型聚合器，并提供了全面的理论分析。在独立同分布（i.i.d）假设下，与现有方法相比，我们的方法具有若干优势。首先，它实现了对$\epsilon$（受攻击客户端比例）的最优依赖。其次，我们的方法无需精确知晓$\epsilon$的值。第三，它允许不同客户端拥有不相等的数据量。随后，我们将分析扩展到非独立同分布（non-i.i.d）数据场景，使得各客户端的数据分布略有不同。