基于表征差异性分析的联邦学习运行时后门检测
Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis
AI总结：
针对联邦学习易受后门攻击且现有检测方法在复杂架构下准确率与运行时有效性不足的问题，提出基于采样的网络表征方法量化客户端差异，并设计迭代算法逐步排除恶意客户端，在基准任务中显著提升了检测准确率与防御有效性，且运行时开销极低。
摘要：
联邦学习（FL）作为一种强大的学习范式，通过聚合来自分布式客户端的模型更新来训练共享模型。然而，模型学习与本地数据的解耦使得FL极易受到后门攻击，单个被攻陷的客户端就能毒化共享模型。尽管近期在后门检测方面取得了进展，但现有方法在检测准确率和运行时有效性方面仍面临挑战，特别是在处理复杂模型架构时。在本研究中，我们提出了一种以准确、稳定且高效的方式检测恶意客户端的新方法。我们的方法利用基于采样的网络表征方法来量化客户端之间的差异，识别由后门注入引起的模型偏差。我们还提出了一种迭代算法，基于这些差异性测量，将恶意客户端作为异常值逐步检测并排除。在一系列基准任务上的评估表明，我们的方法在检测准确率和防御有效性方面优于最先进的方法。在部署用于运行时保护时，我们的方法以边际开销有效消除了后门注入。
英文摘要：
Federated learning (FL), as a powerful learning paradigm, trains a shared model by aggregating model updates from distributed clients. However, the decoupling of model learning from local data makes FL highly vulnerable to backdoor attacks, where a single compromised client can poison the shared model. While recent progress has been made in backdoor detection, existing methods face challenges with detection accuracy and runtime effectiveness, particularly when dealing with complex model architectures. In this work, we propose a novel approach to detecting malicious clients in an accurate, stable, and efficient manner. Our method utilizes a sampling-based network representation method to quantify dissimilarities between clients, identifying model deviations caused by backdoor injections. We also propose an iterative algorithm to progressively detect and exclude malicious clients as outliers based on these dissimilarity measurements. Evaluations across a range of benchmark tasks demonstrate that our approach outperforms state-of-the-art methods in detection accuracy and defense effectiveness. When deployed for runtime protection, our approach effectively eliminates backdoor injections with marginal overheads.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
