计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (20): 106-107.DOI: 10.3778/j.issn.1002-8331.2009.20.032

• 网络、通信、安全 • 上一篇    下一篇

分层神经网络在入侵检测系统中的应用

毕 靖1,张 琨2   

  1. 1.北京建筑工程学院 理学院,北京 100044
    2.河北工业大学 信息工程学院,天津 300130
  • 收稿日期:2009-03-05 修回日期:2009-04-16 出版日期:2009-07-11 发布日期:2009-07-11
  • 通讯作者: 毕 靖

Intrusion detection based on hierarchical neural network

BI Jing1,ZHANG Kun2   

  1. 1.Science School,Beijing University of Civil Engineering and Architecture,Beijing 100044,China
    2.School of Information Engineering,Hebei University of Technology,Tianjin 300130,China
  • Received:2009-03-05 Revised:2009-04-16 Online:2009-07-11 Published:2009-07-11
  • Contact: BI Jing

摘要: 入侵检测技术是提高网络安全的重要手段之一,旨在利用分层神经网络解决入侵检测问题。针对入侵检测研究的通用审计数据集,首先将数据进行预处理以便运算;其次利用RBF网络实现粗检测;再次利用Elman BP网络进行细检测,从而实现分层神经网络的入侵检测;最后在MATLAB平台下进行仿真实验,仿真结果表明,分层神经网络结构在入侵检测中体现出良好的特性。

关键词: 分层神经网络, 入侵检测, 网络安全

Abstract:
Abstract: Intrusion detection is one of important ways to improve network security,and is a main research topic in computer field.The benchmark dataset commonly used in the research of intrusion detection is adopted.Firstly,data are changed into the appropriate type for simulations;Secondly RBF network is used for raw detection;Thirdly Elman BP network is used for advanced detection;Lastly a lot of simulation results are gained from MATLAB platform,and display that hierarchical network is fit for intrusion detection.

Key words: hierarchical network, intrusion detection, network security