SIA OpenIR  > 工业控制网络与系统研究室
Alternative TitleIntrusion detection algorithm based on PCA-OCSVM for industrial control systems
李琳; 尚文利; 姚俊; 万明; 曾鹏
Source Publication计算机工程与设计
Contribution Rank1
Funding Organization国家自然科学基金项目(61501447)
Keyword入侵检测 Ocsvm算法 Modbus Tcp 特征提取 参数优化
Abstract如何有效检测工业病毒对应用层协议的攻击是工业控制系统入侵检测的难点问题。将Modbus TCP协议作为研究对象,结合OCSVM(one class support vector machine,OCSVM)算法,提出一种基于PCA-OCSVM异常检测方法,采用微粒子群优化(particle swarm optimization,PSO)算法对入侵检测模型进行优化。仿真对比分析结果表明,该方法可以高效准确识别攻击或异常行为,实现对工业控制系统的安全防护。
Other AbstractTo detect industry virus attacks to application layer protocol data is a difficult issue in intrusion detection for industrial control systems. PCA-OCSVM intrusion detection method was put forward in which Modbus TCP protocol was taken as research objective and one class support vector (OCSVM) algorithm was combined. Swarm optimization particle (PSO) algorithm was used to optimize the intrusion detection model. Results of simulation show that the proposed method can efficiently and accurately identify the attacks and abnormal behaviors, realizing the security performances of the industrial control system.
Document Type期刊论文
Corresponding Author李琳
Recommended Citation
GB/T 7714
李琳,尚文利,姚俊,等. 工控系统PCA-OCSVM入侵检测算法[J]. 计算机工程与设计,2016,37(11):2928-2933.
APA 李琳,尚文利,姚俊,万明,&曾鹏.(2016).工控系统PCA-OCSVM入侵检测算法.计算机工程与设计,37(11),2928-2933.
MLA 李琳,et al."工控系统PCA-OCSVM入侵检测算法".计算机工程与设计 37.11(2016):2928-2933.
Files in This Item: Download All
File Name/Size DocType Version Access License
工控系统PCA_OCSVM入侵检测算法.(651KB)期刊论文作者接受稿开放获取ODC PDDLView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[李琳]'s Articles
[尚文利]'s Articles
[姚俊]'s Articles
Baidu academic
Similar articles in Baidu academic
[李琳]'s Articles
[尚文利]'s Articles
[姚俊]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[李琳]'s Articles
[尚文利]'s Articles
[姚俊]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 工控系统PCA_OCSVM入侵检测算法.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.