STAR-FL：结合时空分析与鲁棒聚合的安全联邦学习
STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation
查看机构详情
- Ahsanullah University of Science and Technology（阿萨努拉科技大学）
- Florida International University（佛罗里达国际大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对联邦学习面临的定向投毒攻击，提出STAR-FL框架，通过时空聚类识别恶意更新、聚合阶段调整学习率缓解漏检恶意更新影响，实验表明其防御效果优于现有方法且能显著降低攻击成功率。
中文摘要 AI 辅助
数据投毒攻击对计算机视觉领域的联邦学习（Federated Learning, FL）系统构成严重安全威胁。尽管相关研究关注度不断提升，现有防御技术仍存在两大关键挑战：（1）准确区分良性与恶意模型更新；（2）在模型聚合过程中有效缓解投毒模型更新的影响。为应对这些挑战，我们提出一种针对定向投毒攻击的新型防御框架——结合时空分析与鲁棒聚合的联邦学习防御框架（STAR-FL）。首先，我们采用时空聚类方法，在联邦学习训练过程中识别并移除潜在的恶意更新；其次，在聚合阶段调整学习率，以缓解任何未被检测到的恶意更新的影响；最后，我们在多个基准数据集上开展大量实验，评估STAR-FL中时空分析与鲁棒聚合的性能。实验结果表明，二者的协同作用使STAR-FL能够有效保护联邦学习系统，在抵御定向投毒攻击时始终优于现有最先进的防御方法，显著降低攻击成功率（Attack Success Rates, ASRs）。源代码可在该https链接获取。
英文摘要
Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision. Despite growing research attention, two key challenges remain for existing defense techniques: (1) accurately distinguishing between benign and malicious model updates and (2) effectively mitigating the influence of poisoned model updates during model aggregation. To address these challenges, we propose a novel defense framework against targeted poisoning attacks with Spatial-Temporal Analysis and Robust aggregation for FL (STAR-FL). First, we employ spatial-temporal clustering to identify and remove potentially malicious updates from the FL training process. Second, we adjust the learning rate during aggregation to mitigate the impact of any malicious updates that evade detection. Third, we conduct extensive experiments across multiple benchmark datasets to evaluate the spatial-temporal analysis and robust aggregation in STAR-FL. Experimental results demonstrate their synergistic effect in enabling STAR-FL to effectively protect FL and consistently outperform state-of-the-art defenses against targeted poisoning attacks, significantly reducing Attack Success Rates (ASRs). The source code is available at https://github.com/mlsysx/STAR-FL.
