作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2006, Vol. 32 ›› Issue (14): 107-108,. doi: 10.3969/j.issn.1000-3428.2006.14.039

所属专题: 机器学习

• 安全技术 • 上一篇    下一篇

基于机器学习的入侵检测系统研究

王旭仁1,2;许榕生2   

  1. 1. 首都师范大学信息工程学院,北京 100037;2. 中科院高能物理所计算中心,北京 100039
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2006-07-20 发布日期:2006-07-20

Intrusion Detection System Based on Machine Learning

WANG Xuren1,2;XU Rongsheng2   

  1. 1. Information Engineering College, Capital Normal University, Beijing 100037; 2. Computing Center, Institute of High Energy Physics, CAS, Beijing 100039
  • Received:1900-01-01 Revised:1900-01-01 Online:2006-07-20 Published:2006-07-20

摘要: 入侵检测系统存在特征不能自动生成、特征库更新慢、无法适应大量数据等缺点。该文该文提出了基于机器学习的入侵检测系统,将遗传算法和贝叶斯分类算法结合使用,使得检测规则可以自动生成,克服手工编码的不精确、更新慢的缺陷,同时能够处理和分析大数量数据。最后给出了实验分析结果。

关键词: 机器学习, 入侵检测系统, 遗传算法, 贝叶斯分类法

Abstract: Intrusion detection system has some defects, such as signatures being generated manually, updating difficulty and doing nothing in front of large data set. This paper discusses intrusion detection system with machine learning techniques. By making usage of Gene algorithm and Bayes classifiers, the defects mentioned above can be reduced to some extent and some tests have been done to show machine learning magic capability in intrusion detection system.

Key words: Machine learning, Intrusion detection system, Gene algorithm, Bayes classifiers

中图分类号: