融合PCA和PSO-SVM方法在工控入侵检测中的应用

发布时间：2018-05-13 09:28

本文选题：工业控制系统 + 入侵检测　；参考：《科技通报》2017年01期

【摘要】：有效防御病毒对工控系统的入侵是目前工控安全研究的难点问题。为了提高工控系统入侵检测的准确率,本文设计提出了一种主成分分析(PCA)与PSO-SVM相结合的工控入侵检测方法。针对工业控制系统网络数据高维的特性,该方法利用PCA对采集的网络入侵数据进行数据降维与特征提取,支持向量机(SVM)入侵检测的性能主要取决于核函数参数取值的优劣,采用粒子群算法(PSO)对支持向量机参数进行优化,以获得最优的SVM工业控制系统入侵检测模型。采用密西西比州立大学关键基础设施保护中心最新提出的工控标准数据集进行仿真实验,结果表明该算法在攻击检测与攻击类型识别方面均有较高的查准率,提高了工业控制系统的安全性能。
[Abstract]:Preventing the invading of industrial control system by virus effectively is a difficult problem in the research of industrial control security. In order to improve the accuracy of intrusion detection in industrial control system, a new intrusion detection method based on principal component analysis (PCA) and PSO-SVM is proposed in this paper. Aiming at the characteristic of high dimension of network data in industrial control system, this method uses PCA to reduce dimension and feature extraction of collected network intrusion data. The performance of support vector machine (SVM) intrusion detection mainly depends on the value of kernel function parameter. Particle swarm optimization (PSO) is used to optimize the parameters of support vector machine (SVM) to obtain the optimal intrusion detection model of SVM industrial control system. The simulation experiment is carried out by using the latest industrial control standard data set proposed by the key Infrastructure Protection Center of Mississippi State University. The results show that the algorithm has a high precision in attack detection and attack type recognition. The safety performance of industrial control system is improved.
【作者单位】：华东理工大学化工过程先进控制和优化技术教育部重点实验室;中国信息安全测评中心;
【基金】：国家自然科学青年基金(51407078)
【分类号】：TP273;TP18

【相似文献】