计算机应用 ›› 2011, Vol. 31 ›› Issue (12): 3337-3339.

• 信息安全 • 上一篇    下一篇

基于SVM协作训练的入侵检测方法研究

邬书跃1,2,余杰3,樊晓平2   

  1. 1. 湖南涉外经济学院 电气与信息工程学院,长沙 410205
    2. 中南大学 信息科学与工程学院,长沙 410083
    3. 国防科学技术大学 计算机学院, 长沙 410073
  • 收稿日期:2011-05-26 修回日期:2011-07-13 发布日期:2011-12-12 出版日期:2011-12-01
  • 通讯作者: 余杰
  • 基金资助:
    国家核高基项目;湖南省自然科学基金资助项目(07JJ6124);国家自然科学基金资助项目

Improved SVM co-training based intrusion detection

WU Shu-yue1,2,YU Jie3,FAN Xiao-ping2   

  1. 1. College of Electrical and Information Engineering, Hunan International Economics University, Changsha Hunan 410205,China
    2. School of Information Science and Engineering,Central South University, Changsha Hunan 410083,China
    3. School of Computer Science, National University of Defense Technology, Changsha Hunan 410073,China
  • Received:2011-05-26 Revised:2011-07-13 Online:2011-12-12 Published:2011-12-01
  • Contact: YU Jie

摘要: 提出了在少量样本条件下,采用带变异因子的支持向量机(SVM)协作训练模型进行入侵检测的方法。充分利用大量未标记数据,通过两个分类器检测结果之间的迭代训练,可以提高检测算法的准确度和稳定性。在协作训练的多次迭代之间引入变异因子,减小由于过学习而降低训练效果的可能。仿真实验表明,该方法的检测准确度比传统的SVM算法提高了7.72%,并且对于训练数据集和测试数据集的依赖程度都较低。

关键词: 入侵检测, 支持向量机, 协作训练, 小样本, 分类器

Abstract: In this paper, a Support Vector Machine (SVM) co-training based method with variation factors to detect network intrusion was proposed. It made full use of the large amount of unlabeled data, and increased the detection accuracy and stability by co-training two classifiers. It further introduced variation factors among multiple iterations to decrease the possibility of effect reduction due to over-learning. The simulation results show that the proposed method is 7.72% more accurate than the traditional SVM method, and it depends less on the training dataset and test dataset.

Key words: Intrusion Detection, Support Vector Machine (SVM), Co-training, Small Sample, Classifier

中图分类号: