Anomaly Detection Method of Power Internet of Things Terminals in Zero-Trust Environment
简介：With more and more IoT terminals being deployed in various power grid business scenarios,ter-minal reliability has become a practical challenge that threatens the current security protection architecture.Most IoT terminals have security risks and vulnerabil-ities,and limited resources make it impossible to de-ploy costly security protection methods on the termi-nal.In order to cope with these problems,this paper proposes a lightweight trust evaluation model TCL,which combines three network models,TCN,CNN,and LSTM,with stronger feature extraction capabil-ity and can score the reliability of the device by pe-riodically analyzing the traffic behavior and activity logs generated by the terminal device,and the trust evaluation of the terminal's continuous behavior can be achieved by combining the scores of different peri-ods.After experiments,it is proved that TCL can ef-fectively use the traffic behaviors and activity logs of terminal devices for trust evaluation and achieves F1-score of 95.763,94.456,99.923,and 99.195 on HDFS,BGL,N-BaIoT,and KDD99 datasets,respectively,and the size of TCL is only 91KB,which can achieve similar or better performance than CNN-LSTM,Ro-bustLog and other methods with less computational resources and storage space.展开
学者：SunPengzhanRenYinlinSHAOSujieYangChaoQiuXuesong
关键词：Anomaly detectiondistributed machine learningPower Internet of ThingsZero trust
在线出版日期：2026-03-17 （网站首发日期）
