计算机工程 ›› 2008, Vol. 34 ›› Issue (4): 13-15.doi: 10.3969/j.issn.1000-3428.2008.04.005

• 博士论文 • 上一篇    下一篇

基于粒子群优化和模糊c均值聚类的入侵检测

唐贤伦1,2,庄 陵1,2,李银国1,曹长修2   

  1. (1. 重庆邮电大学自动化学院,重庆 400065;2. 重庆大学自动化学院,重庆 400044)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-02-20 发布日期:2008-02-20

Intrusion Detection Based on Particle Swarm Optimizationand Fuzzy c-means Clustering

TANG Xian-lun1,2, ZHUANG Ling1,2, LI Yin-guo1, CAO Chang-xiu2   

  1. (1. College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065;2. College of Automation, Chongqing University, Chongqing 400044)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-02-20 Published:2008-02-20

摘要: 针对模糊c均值算法对初始化敏感及易陷入局部极值的问题,利用粒子群优化算法的全局优化性能,结合模糊c均值聚类算法,提出基于粒子群优化和模糊c均值聚类的入侵检测方法。该方法可快速得到全局最优聚类,并且有效检测出未知的攻击。实验表明该方法不仅对未知攻击有较好的检测效果,而且具有较低的误报率和较高的检测率。

关键词: 入侵检测, 模糊c均值聚类, 粒子群优化

Abstract: A novel intrusion detection method based on Particle Swarm Optimization(PSO) and Fuzzy c-Means Clustering(FCM) is proposed in order to solve the problem of FCM which is much more sensitive to the initialization and easier to fall into local optimization. The method can quickly obtain global optimal clustering and can detect unknown intrusions efficiently. Experimental results show that the method can detect unknown intrusions with lower false positive rate and higher true positive rate.

Key words: intrusion detection, fuzzy c-means clustering, particle swarm optimization

中图分类号: