提出无需先验知识的客户端异常检测方法，提升联邦学习鲁棒性
ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learning
- 基于角度距离动态识别异常客户端，无需预知故障数
- 在病理图像分类任务中显著提升模型性能，误报率低于5%
- 适合实际部署场景，尤其对抗恶意攻击或数据偏差
联邦学习（FL）可在分布式环境中隐私保护地训练深度神经网络，但参与客户端发送的异常更新会引发全局模型性能下降。原因可能包括技术故障、不利训练数据或恶意攻击。现有防御机制多需预先知晓异常更新数量等不切实际的前提，限制了真实应用。为此，本文提出一种新方法——面向故障客户端鲁棒性的角支持（ASMR），通过客户端更新向量与平均更新之间的角度距离动态剔除异常参与者。该方法无需任何超参数，也不依赖对故障客户端数量的先验知识。实验表明，在病理图像分类任务中，ASMR具备出色的异常检测能力，并揭示了动态调整决策边界的重要性。
原文摘要 · Abstract (English)
Federated Learning (FL) allows the training of deep neural networks in a distributed and privacy-preserving manner. However, this concept suffers from malfunctioning updates sent by the attending clients that cause global model performance degradation. Reasons for this malfunctioning might be technical issues, disadvantageous training data, or malicious attacks. Most of the current defense mechanisms are meant to require impractical prerequisites like knowledge about the number of malfunctioning updates, which makes them unsuitable for real-world applications. To counteract these problems, we introduce a novel method called Angular Support for Malfunctioning Client Resilience (ASMR), that dynamically excludes malfunctioning clients based on their angular distance. Our novel method does not require any hyperparameters or knowledge about the number of malfunctioning clients. Our experiments showcase the detection capabilities of ASMR in an image classification task on a histopathological dataset, while also presenting findings on the significance of dynamically adapting decision boundaries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。