研究人员开发了一种名为EnCAgg的新方法，以提高联邦学习在面对动态模型投毒攻击时的鲁棒性。该方法使用一小组已知的良性客户端作为参考，以准确识别和过滤恶意梯度。该方法在低维空间中结合了基于密度的聚类和一个梯度生成器模型，以重新连接稀疏的良性梯度，最终允许更多合法的参与聚合过程。 AI
影响 增强了联邦学习系统的安全性，使得协作模型训练更加可靠。
排序理由 该集群包含一篇详细介绍联邦学习新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.22506v1 Announce Type: cross Abstract: Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed thresholds or perform clustering with a fixed number of clu…
Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed thresholds or perform clustering with a fixed number of clusters to distinguish malicious gradients from beni…