用逻辑推理检测恶意客户端，提升时序联邦学习安全性。
LOGSAFE: Logic-Guided Verification for Trustworthy Federated Time-Series Learning
- 通过提取时序特性并推理全局规律判断客户端可信度
- 在实验中误差比最优基线降低93.27%
- 适合关注工业物联网安全的科研与工程人员
本文提出LOGSAFE，一种面向时序联邦学习的防御机制，尤其适用于网络物理系统。针对投毒攻击，它突破传统更新相似性方法，转而采用逻辑推理评估客户端可靠性。LOGSAFE提取客户端特有的时间属性，推断全局模式，并以此验证客户端以识别并剔除恶意参与方。实验表明，其性能显著优于现有方法，在误差控制上相比次优基线最高实现93.27%的降低。代码已公开于https://github.com/judydnguyen/LOGSAFE-Robust-FTS。
原文摘要 · Abstract (English)
This paper introduces LOGSAFE, a defense mechanism for federated learning in time series settings, particularly within cyber-physical systems. It addresses poisoning attacks by moving beyond traditional update-similarity methods and instead using logical reasoning to evaluate client reliability. LOGSAFE extracts client-specific temporal properties, infers global patterns, and verifies clients against them to detect and exclude malicious participants. Experiments show that it significantly outperforms existing methods, achieving up to 93.27% error reduction over the next best baseline. Our code is available at https://github.com/judydnguyen/LOGSAFE-Robust-FTS.
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。