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.

翻译：本文提出LOGSAFE，一种面向时序场景（尤其是在信息物理系统中）的联邦学习防御机制。该机制超越传统的基于更新相似度的方法，转而采用逻辑推理来评估客户端的可靠性，从而应对投毒攻击。LOGSAFE提取客户端特定的时序属性，推断全局模式，并依据这些模式对客户端进行验证，以检测并排除恶意参与者。实验表明，该方法显著优于现有方案，相较于次优基线，错误率降低高达93.27%。我们的代码开源在https://github.com/judydnguyen/LOGSAFE-Robust-FTS。