高级检索

  • ISSN 1006-3080
  • CN 31-1691/TQ

基于改进蝙蝠算法的工业控制系统入侵检测

李金乐 王华忠 陈冬青

李金乐, 王华忠, 陈冬青. 基于改进蝙蝠算法的工业控制系统入侵检测[J]. 华东理工大学学报(自然科学版), 2017, (5): 662-668. doi: 10.14135/j.cnki.1006-3080.2017.05.010
引用本文: 李金乐, 王华忠, 陈冬青. 基于改进蝙蝠算法的工业控制系统入侵检测[J]. 华东理工大学学报(自然科学版), 2017, (5): 662-668. doi: 10.14135/j.cnki.1006-3080.2017.05.010
LI Jin-le, WANG Hua-zhong, CHEN Dong-qing. Intrusion Detection of Industrial Control System Based on Improved Bat Algorithm[J]. Journal of East China University of Science and Technology, 2017, (5): 662-668. doi: 10.14135/j.cnki.1006-3080.2017.05.010
Citation: LI Jin-le, WANG Hua-zhong, CHEN Dong-qing. Intrusion Detection of Industrial Control System Based on Improved Bat Algorithm[J]. Journal of East China University of Science and Technology, 2017, (5): 662-668. doi: 10.14135/j.cnki.1006-3080.2017.05.010

基于改进蝙蝠算法的工业控制系统入侵检测

doi: 10.14135/j.cnki.1006-3080.2017.05.010

Intrusion Detection of Industrial Control System Based on Improved Bat Algorithm

  • 摘要: 针对蝙蝠算法(BA)易陷入局部极小的缺点,提出了两点改进:(1)在蝙蝠位置更新时考虑了当前局部最优解分布对算法的影响;(2)将差分进化算法(DE)中的变异操作迁移到蝙蝠算法中,采用随机性变异的方式增加了种群多样性,提升了算法局部搜索能力,并通过典型测试函数验证了本文算法的优越性。将该算法用于工业控制系统(ICS)入侵检测中支持向量机(SVM)分类器的参数优化,使用工控入侵检测标准数据集进行仿真研究。结果表明,与DE、粒子群算法(PSO)和遗传算法(GA)等优化算法相比,其优化的SVM入侵检测模型在检测率、漏报率和误报率等指标上都有显著提升。

     

  • [1] JIANG J,YASAKETHU L.Anomaly detection via one class svm for protection of scada systems[C]//2013 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (Cyber C).USA:IEEE,2013:82-88.
    [2] NADER P,HONEINE P,BEAUSEROY P.One-class classification for intrusion detection in SCADA systems[J].IEEE Transactions on Industrial Informatics,2014,10(4):2308-2317.
    [3] YOO H,SHON T.Novel approach for detecting network anomalies for substation automation based on IEC 61850[J].Multimedia Tools and Applications,2015,74(1):303-318.
    [4] BERE M,MUYINGI H.Initial investigation of industrial control system (ICS) security using artifiicial inmue system (AIS)[C]//Internation Conference on Emerging Trends in Networks and Computer Communication.USA:IEEE,2015:79-84.
    [5] GAO W,MORRIS T,REAVES B,et al.On SCADA control system command and response injection and intrusion detection[C]//eCrime Researchers Summit (eCrime),2010.USA:IEEE,2010:1-9.
    [6] BEAVER J M,BORGES-HINK R C,BUCKNER M A.An evaluation of machine learning methods to detect malicious SCADA communications[C]//International Conference on Machine Learning and Applications.USA:IEEE,2013:54-59.
    [7] 王华忠,杨智慧,颜秉勇,等.融合PCA和PSO-SVM方法在工控入侵检测中的应用[J].科技通报,2016(1):80-85.
    [8] 尚文利,李琳,万明,等.基于优化单类支持向量机的工业控制系统入侵检测算法[J].信息与控制,2015,44(6):678-684.
    [9] 郑云水,岳小雪,林俊亭.带有高斯变异的混合蛙跳蝙蝠算法[J].计算机应用研究,2015,32(12):3629-3633.
    [10] 刘羿.蝙蝠算法优化神经网络的网络入侵检测[J].计算机仿真,2015,32(2):311-314.
    [11] 肖辉辉,段艳明.基于DE算法改进的蝙蝠算法的研究及应用[J].计算机仿真,2014,31(1):272-277.
    [12] 龙文,张文专.求解约束优化问题的改进蝙蝠算法[J].计算机应用研究,2014,31(8):2350-2353.
    [13] GAO W.Cyberthreats attacks and intrusion detection in supervisory control and data acquistion networks[M].[s.l.]:Dissertations & Theses-Gradworks,2013.
  • 加载中
图(1)
计量
  • 文章访问数:  1511
  • HTML全文浏览量:  191
  • PDF下载量:  426
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-11-15
  • 刊出日期:  2017-10-28

目录

    /

    返回文章
    返回