Threats,attacks and defenses to federated learning:issues,taxonomy and perspectives  

作　　者：Pengrui Liu Xiangrui Xu Wei Wang 

机构地区：[1]Beijing Key Laboratory of Security and Privacy in Intelligent Transportation,Beijing Jiaotong University,Beijing,100044,China

出　　处：《Cybersecurity》2022年第2期56-74,共19页网络空间安全科学与技术（英文）

基　　金：This work was supported in part by National Key R&D Program of China,under Grant 2020YFB2103802;in part by the National Natural Science Foundation of China,uder grant U21A20463;in part by the Fundamental Research Funds for the Central Universities of China under Grant KKJB320001536.

摘　　要：Empirical attacks on Federated Learning(FL)systems indicate that FL is fraught with numerous attack surfaces throughout the FL execution.These attacks can not only cause models to fail in specific tasks,but also infer private information.While previous surveys have identified the risks,listed the attack methods available in the literature or provided a basic taxonomy to classify them,they mainly focused on the risks in the training phase of FL.In this work,we survey the threats,attacks and defenses to FL throughout the whole process of FL in three phases,including Data and Behavior Auditing Phase,Training Phase and Predicting Phase.We further provide a comprehensive analysis of these threats,attacks and defenses,and summarize their issues and taxonomy.Our work considers security and privacy of FL based on the viewpoint of the execution process of FL.We highlight that establishing a trusted FL requires adequate measures to mitigate security and privacy threats at each phase.Finally,we discuss the limitations of current attacks and defense approaches and provide an outlook on promising future research directions in FL.

关 键 词：Federated learning Security and privacy threats Multi-phases Inference attacks Poisoning attacks Evasion attacks DEFENSES TRUSTED 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]