一种基于集成学习的工业控制系统入侵检测方法

摘要

Disclosed by the present invention is an industrial control system intrusion detection method based on integrated learning, the method comprising: acquiring field data of an industrial control system, carrying out message parsing on communication data to obtain a structured sample, selecting an appropriate feature set by means of feature screening and extraction, inputting the feature set into an integrated learning model consisting of a plurality of machine learning algorithms, and finally determining whether communication data of a specific industrial control system is normal or abnormal by means of the learning algorithm. According to the present invention, effective information of the communication data of the industrial control system is fully mined by utilizing an intelligent learning algorithm, and the intrusion detection accuracy is effectively improved by means of an integrated learning model fusion method, thereby reducing the missing report rate.