Journal of Computer Applications ›› 2005, Vol. 25 ›› Issue (09): 2078-2079.DOI: 10.3724/SP.J.1087.2005.02078

• Network and information security • Previous Articles     Next Articles

Research of host intrusion detection systems based on levenberg-marquardt algorithm

WANG Zi-min1,2,WANG Yong1,TAN Yong-hong1   

  1. 1.Lab of Intelligent Systems and Control Engineering,Guilin University of Electronic Technology,Guilin Guangxi 541004,China;2.School of Electronic Engineering,Xidian University,Xi’an Shaanxi 710071,China
  • Online:2011-04-11 Published:2005-09-01

基于Levenberg-Marquardt算法的主机入侵检测系统研究

王子民1,2,王勇1,谭永红1   

  1. 1.桂林电子工业学院智能系统与工业控制研究室; 2.西安电子科技大学电子工程学院
  • 基金资助:

    广西区教育厅资助项目(D200126)

Abstract: Intrusion Detection System(IDS) is one of the research hotspots in the field of Information Security.The Levenberg-Marquardt algorithm was taken to optimize traditional BP Neural Network,and the LMBP algorithm was successfully applied to host intrusion detection systems.Then an LMBP-HIDS intrusion detection systems model was built.The result indicated that by using Levenberg-Marquardt algorithm to optimize BP Neural Network,the BP Neural Network could work more efficiently in Intrusion Detection Systems.It could improve the training speed,shorten the training process.

Key words: information security, intrusion detection, neural network, BP Neural Network,, Levenberg-Marquart algorithm, LMBP-HIDS

摘要: 入侵检测系统是当前信息安全领域的研究热点,在保障信息安全方面起着重要的作用。对BP神经网络优化算法进行对比研究的基础上,利用Levenberg-Marquardt算法对传统BP算法进行改进,成功地将LMBP算法运用到基于W indows操作系统的主机入侵检测中去,建立LMBP-HIDS入侵检测系统模型。实验结果表明,运用Levenberg-Marquardt算法优化BP神经网络进行主机入侵检测,可以较好地提高学习速率,缩短训练过程。

关键词: 信息安全, 入侵检测, 神经网络, BP神经网络, LM算法, LMBP-HIDS

CLC Number: