首页 | 官方网站   微博 | 高级检索  
     

基于协议分析和SVM多分类的入侵检测系统研究
引用本文:段军,林立友.基于协议分析和SVM多分类的入侵检测系统研究[J].包头钢铁学院学报,2011,30(1).
作者姓名:段军  林立友
作者单位:段军,DUAN Jun(内蒙古科技大学科技处,内蒙古包头,014010);林立友,LIN Li-you(内蒙古科技大学信息工程学院,内蒙,古包头,014010)
摘    要:入侵检测实质上可以被描述为对数据样本进行尽可能正确的分类,关键问题是特征选择和模式识别方法的选择.采用SVM分类器组合的方法对数据样本进行分类,结合协议分析技术,提出了基于协议分析和SVM多分类的入侵检测系统模型,并利用KDD CUP 99数据集对系统模型进行测试.测试结果表明,所提出的方法有效提高了入侵检测的效率,降低了漏报率和误报率.

关 键 词:入侵检测  协议分析  支持向量机  SVM多分类

Intrusion detection system based on protocol analysis and SVM multi-classification
DUAN Jun,LIN Li-you.Intrusion detection system based on protocol analysis and SVM multi-classification[J].Journal of Baotou University of Iron and Steel Technology,2011,30(1).
Authors:DUAN Jun  LIN Li-you
Affiliation:DUAN Jun1,LIN Li-you2(1.Department of Science and Technology,Inner Mongolia University of Science and Technology,Baotou 014010,China,2.Information Engineering School,China)
Abstract:Intrusion detection can be essentially described as the classification of data samples as correctly as possible.The key problem is feature selection and choice of pattern recognition methods.The method of combined SVM classifiers was utilized to classify the data samples in combination with protocol analysis techniques.Intrusion detection system model was proposed based on protocol analysis and SVM multi-classification,and the system model was tested using KDD CUP 99data sets.The test result indicates that ...
Keywords:intrusion detection  protocol analysis  support vector machine  multi-call SVM  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号