北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2016, Vol. 39 ›› Issue (s1): 14-18.doi: 10.13190/j.jbupt.2016.s.004

• 论文 • 上一篇    下一篇

工控设备状态检测中BP神经网络模型的应用

姚赟政1,2, 杨安1, 石志强1, 孙利民1   

  1. 1. 中国科学院信息工程研究所 物联网信息安全技术北京市重点实验室, 北京 100093;
    2. 北京航空航天大学 软件学院, 北京 100191
  • 收稿日期:2015-12-01 出版日期:2016-06-28 发布日期:2016-06-28
  • 作者简介:姚赟政(1990-),男,硕士生,E-mail:yao_yunzheng@126.com;孙利民(1966-),男,博士,研究员.
  • 基金资助:

    中国科学院国防科技创新基金项目重点基金(CXJJ-14-Z68);国家自然科学基金项目(61402476);新疆自治区科技专项项目(201230122)

Application of BP Neural Network Model in Device State Detection of Industrial Control System

YAO Yun-zheng1,2, YANG An1, SHI Zhi-qiang1, SUN Li-min1   

  1. 1. Key Laboratory of Networking Information Security Technology of the Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China;
    2. School of Saftware, Beihang University, Beijing 100093, China
  • Received:2015-12-01 Online:2016-06-28 Published:2016-06-28

摘要:

针对工控系统现场网中的物理设备状态信息,提出一种利用BP神经网络模型实时分析和判断设备是否处于正常运行状态的入侵检测算法.该算法旨在能够发现来自工控系统内外部的入侵行为和合法控制指令被恶意利用的复杂攻击.

关键词: 工业控制系统, 设备状态, BP神经网络, 入侵检测

Abstract:

The industrial control system (ICS) security is closely related to the security of national critical infrastructure, so, more and more countries began to increase the importance of ICS. Aiming at the physical devices in ICS field control net, an innovative intrusion detection algorithm was presented to analysis and estimate whether the devices are in normal operation condition. This algorithm is designed to detect internal or external intrusion actions in ICS and complex attack by maliciously using normative control commands.

Key words: industrial control system, device status, back propagation neural network, intrusion detection

中图分类号: