发表机构
Ocean College, Zhejiang University; City University of Hong Kong; Aalto University（浙江大学海洋学院; 香港城市大学; 阿尔托大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对联邦学习中恶意攻击和数据异构性问题，提出利用截断二次损失的新鲁棒聚合规则，减轻现有方法偏差，在非凸损失函数和异构数据下实现最优阶拜占庭鲁棒学习，实验证明该聚合器鲁棒性优于其他技术。
AI 中文摘要
联邦学习在n个客户端之间分发数据，容易受到恶意攻击和数据异构性影响，给鲁棒学习带来挑战。为解决此问题，已采用中心裁剪和Huber聚合器来实现拜占庭鲁棒性。本文首先通过凸共轭理论证明它们的等价性，并表明在存在异常值时会产生有偏差的解，在高数据异构性和大量异常值情况下会导致失败。接着提出利用截断二次（TQ）损失的新鲁棒聚合规则，有效减轻现有方法的偏差。证明该聚合器在非凸损失函数和异构数据下实现最优阶拜占庭鲁棒学习，提高联邦学习系统可靠性。还提供TQ的鲁棒偏差估计策略并证明其有效性，表明TQ即使在仅知道拜占庭客户端数量估计时也保持鲁棒性。最后在MNIST、Fashion-MNIST和CIFAR-10上的实验结果表明，该聚合器比竞争技术具有更好的鲁棒性性能。
英文摘要
Federated learning distributes data among $n$ clients, making it vulnerable to malicious attacks and data heterogeneity, which together pose challenges for robust learning. To tackle this issue, centered clipping and Huber aggregators have been exploited for Byzantine robustness. In this paper, we first demonstrate their equivalence via convex conjugate theory, and show that they can yield biased solutions in the presence of outliers, leading to failure under high data heterogeneity and a substantial fraction of outliers. Next, we propose a new robust aggregation rule that utilizes the truncated-quadratic (TQ) loss, effectively mitigating the biases of existing methods, such as centered clipping and Huber aggregators. We show that our aggregator achieves order-optimal Byzantine-robust learning under nonconvex loss functions and heterogeneous data, ultimately enhancing the reliability of federated learning systems. Additionally, we provide a robust deviation estimation strategy for TQ, demonstrating its effectiveness. Furthermore, we show that TQ maintains robustness even when only an estimate of the number of Byzantine clients is available. Finally, experimental results on MNIST, Fashion-MNIST, and CIFAR-10, indicate that our aggregator provides better robustness performance than the competing techniques.
