Abstract：With the advent of the Industry 4.0 era,the relationship between industrial resources,data and the Internet is getting closer.However,the use of a large amount of information technology also brings huge hidden dangers to industrial control systems (ICS).With the increase of various attack methods,the existing anomaly detection methods have many limitations and cannot effectively identify various attacks.In view of the above situation,this paper proposes an industrial anomaly intrusion detection method based on ant colony algorithm and reinforcement learning.The ant colony algorithm is used for feature selection,and irrelevant and redundant features are eliminated through multiple iterations,making it suitable for model processing and improving training speed.The algorithm has faster convergence in the process of selecting feature subsets,which can avoid blind search and find the optimal solution quickly.This article modifies the paradigm of deep reinforcement learning,and uses its feedback learning and decision-making capabilities to classify different types of attacks.This paper uses real data collected by the SCADA system,a natural gas pipeline testing platform designed and developed by Mississippi State University,to evaluate the model.Experimental results show that this method can meet the demand for detecting attacks.
陈铁明,董航. 使用蚁群算法和深度强化学习的工业异常入侵检测[J]. 小型微型计算机系统, 2022, 43(4): 779-784.
CHEN Tie-ming,DONG Hang. Industrial Anomaly Intrusion Detection Using Ant Colony Algorithm and Deep Reinforcement Learning. Journal of Chinese Computer Systems, 2022, 43(4): 779-784.
2022, Vol. 43 
