Most existing Byzantine-robust federated learning (FL) methods suffer from slow and unstable convergence. Moreover, when handling a substantial proportion of colluded malicious clients, achieving robustness typically entails compromising model utility. To address these issues, this work introduces FedIDM, which employs distribution matching to construct trustworthy condensed data for identifying and filtering abnormal clients. FedIDM consists of two main components: (1) attack-tolerant condensed data generation, and (2) robust aggregation with negative contribution-based rejection. These components exclude local updates that (1) deviate from the update direction derived from condensed data, or (2) cause a significant loss on the condensed dataset. Comprehensive evaluations on three benchmark datasets demonstrate that FedIDM achieves fast and stable convergence while maintaining acceptable model utility, under multiple state-of-the-art Byzantine attacks involving a large number of malicious clients.

翻译：现有的大多数拜占庭鲁棒联邦学习方法存在收敛缓慢且不稳定的问题。此外，在处理大量合谋恶意客户端时，实现鲁棒性通常需要牺牲模型效用。为解决这些问题，本文提出FedIDM，该方法利用分布匹配构建可信压缩数据，用于识别和过滤异常客户端。FedIDM包含两个主要组件：（1）抗攻击的压缩数据生成，以及（2）基于负贡献拒绝的鲁棒聚合。这些组件会排除满足以下条件的本地更新：（1）偏离由压缩数据导出的更新方向，或（2）在压缩数据集上造成显著损失。在三个基准数据集上的综合评估表明，在多种涉及大量恶意客户端的最新拜占庭攻击下，FedIDM在保持可接受模型效用的同时，实现了快速稳定的收敛。