检索
E-mail
RSS
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 ›› 2009, Vol. 35 ›› Issue (2): 208-209,.doi: 10.3969/j.issn.1000-3428.2009.02.073

• 人工智能及识别技术 • 上一篇    下一篇

入侵检测的进化神经网络研究

易晓梅1,2，陈 波1，蔡家楣1   

  1. (1. 浙江工业大学软件学院，杭州 310023；2. 浙江林学院信息工程学院，临安 311300)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-01-20 发布日期:2009-01-20

Research on Evolutionary Neural Network of Intrusion Detection

YI Xiao-mei1,2, CHEN Bo1, CAI Jia-mei1   

  1. (1. College of Software, Zhejiang University of Technology, Hangzhou 310023; 2. School of Information Engineering, Zhejiang Forestry College, Lin’an 311300)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-01-20 Published:2009-01-20

PDF

1209

被引次数

17 | 7

摘要： 针对传统入侵检测系统漏报率和误报率高的问题，提出基于遗传神经网络的入侵检测系统。该系统将遗传算法和BP算法有机结合，利用遗传算法较强的宏观搜索能力和全局寻优特点，优化BP网络的初始权值和阈值，并在此基础上进行神经网络学习，从而建立入侵检测系统的优化分析模型。实验结果表明，该算法可以有效地运用于入侵检测系统中。

关键词: 神经网络, 遗传算法, 入侵检测

Abstract: Aiming at the problem of the higher rate of losing alarm and false alarm in traditional intrusion detection system, a novel intrusion detection system based on genetic neural network is proposed, which combines genetic algorithm with BP algorithm to optimize the initial values of weights and bias of BP network by using the characteristic of strong macro search ability and optimization in overall situation. On basis of this, the neural network study is conducted, and the optimized analysis model of intrusion detection system is set up. Experimental results show this algorithm can be applied to this intrusion detection system effectively.

Key words: neural network, Genetic Algorithm(GA), intrusion detection

中图分类号: