基于改进的小波神经网络入侵预测算法研究  

Research on Intrusion Prediction Algorithm Based on Modified Wavelet Neural Network

作　　者：胡津铭 张艳[1] 陆臻[1] 周嵩岑 HU Jin-ming;ZHANG Yan;LU Zhen;ZHOU Song-cen(The Third Research Institute of Ministry of Public Security,Shanghai 200031,China)

机构地区：[1]公安部第三研究所,上海200031

出　　处：《计算机仿真》2021年第9期405-408,共4页Computer Simulation

基　　金：上海市2018年度“科技创新行动计划”高新技术领域项目(18511105700)。

摘　　要：随着信息技术的不断发展,网络服务逐渐成为人们生活的重要组成部分。与此同时,日益严重的网络安全问题,也给人们的信息和财产安全带来了巨大的安全隐患。入侵检测系统(Intrusion detection system,IDS)作为信息安全领域的研究热点之一,可以根据预定的规则扫描网络活动,监控网络流量,提供实时告警。然而IDS也存在着突出的问题,例如缺乏主动防御能力、检测落后于入侵等。因此,基于改进的小波神经网络提出一种入侵预测算法,并将其应用于入侵防御系统(Intrusion prevention system,IPS)中,提高对于网络入侵的预测精度。仿真结果表明,较之传统的小波神经网络,所提预测模型拥有更高的检测率和更低的误报率,可以更好地保障计算机系统的安全。With the development of information technology,network services have gradually become an important part of people’s lives.Meanwhile,network security issues are increasingly more serious,which brings great security risks to people’s information and property security.As one of the hot research topics in the information security field,the intrusion detection system can scan network activities according to predetermined rules,monitor network traffic and provide a real-time alarm.However,intrusion detection system still has outstanding problems,such as lack of active defense capabilities,detection behind the intrusion,etc.In this paper,we propose a network intrusion prediction method using a modified wavelet neural network and apply it to the intrusion prevention system to improve the prediction accuracy of network intrusion.Simulation results show that the proposed method can obtain better prediction accuracy and lower false alarm rate compared with the traditional wavelet neural network,which can better guarantee the security of the computer system.

关 键 词：网络安全 入侵检测 入侵预测 改进的小波神经网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]