计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (28): 80-82.

• 网络、通信、安全 • 上一篇    下一篇

基于QPSO优化投影寻踪的网络入侵检测方法

朱丽华,刘以安,魏 敏   

  1. 江南大学 信息工程学院,江苏 无锡 214122
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-10-01 发布日期:2011-10-01

Network intrusion detection method based on QPSO optimization projection pursuit algorithm

ZHU Lihua,LIU Yi’an,WEI Min   

  1. School of Information Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-10-01 Published:2011-10-01

摘要: 为了提高入侵检测系统的检测率,降低误报率,提出应用QPSO搜索投影寻踪最优投影方向的入侵检测算法,并利用投影寻踪和聚类相结合的思想将网络检测数据的多特征属性投影到低维进行聚类识别判定。对训练样本中的数据进行预处理并且归一化,获取最优投影方向,让样本数据投影到低维空间,对检测数据进行聚类判定。实验结果表明,该方法能很有效地提高入侵检测性能。

关键词: 投影寻踪, 入侵检测, 量子粒子群算法

Abstract: Existing intrusion detection systems have many problems such as detection rate,false positive rate.An intrusion detection based on optimization projection pursuit algorithm is proposed.Aimed at the optimization problem of calculating the best projected vector of projection pursuit,a method is used based on QPSO.Optimization projection pursuit algorithm is implemented to project the data of feature from high dimension to low dimension,then the category of the network data is determined by the clustering algorithm.The algorithm includes data preconditioning,data normalized,the best projected vector calculation,data project to low dimension,and finally inspects data categorization.The experimental results show that the performance of the present method is feasible and effective.

Key words: projection pursuit, intrusion detection, Quantum Particle Swarm Optimization(QPSO)