Intrusion Detection Method Based on Classify Support Vector Machine

摘要：

Aimed at the network intrusion behaviors are characterized with uncertainty, complexity, diversity and dynamic tendency and the advantages of support vector machine (SVM), an intrusion detection method based on classify SVM is presented in this paper. The SVM network structure for intrusion detection is established, and use the genetic algorithm (GA) to optimize SVM parameters, thereby enhancing the convergence rate and the detection accuracy. We discussed and analyzed the affect factors of network intrusion behaviors. With the ability of strong selflearning and well generalization of SVM, the intrusion detection method based on classify SVM can detect various intrusion behaviors rapidly and effectively by learning the typical intrusion characteristic information. The experimental result shows that this intrusion detection method is feasible and effective.

关键词： intrusion detection support vector machine genetic algorithm intrusion behaviors

作者: Meijuan Gao Jingwen Tian Mingping Xia

作者单位: College of Automation Beijing Union University Beijing, China

会议类型: 国际会议

会议名称: 2009 Second International Conference on Intelligent Computation Technology and Automation(2009 第二届IEEE智能计算与自动化国际会议 ICICTA 2009)

会议地点: 长沙

会议语种:英文

页码: 1343-1346

在线出版日期: 2009-10-10（万方平台首次上网日期，不代表论文的发表时间）