基于流量预测的Ad hoc网络入侵检测方案  

Intrusion detection system in Ad Hoc networks based on network traffic prediction

作　　者：谭铣康[1] 刘渊[2] 刘涛[1] 张恬[1] 

机构地区：[1]江南大学信息工程学院,江苏无锡214122 [2]江南大学数字媒体学院,江苏无锡214122

出　　处：《计算机工程与设计》2011年第6期1949-1951,1956,共4页Computer Engineering and Design

基　　金：江苏省科技支撑计划基金项目(BE2009009);无锡市科技计划基金项目(CMEF09002)

摘　　要：Ad hoc网络具有无线传输的介质、动态改变的拓扑、缺乏监督等特点,为解决其安全防御问题,提出并实现了基于网络流量预测的Ad hoc入侵检测系统。该系统主要包括节点检测和响应系统两个部分,网络中的节点采用节点检测引擎对网络流量进行预测,根据原始流量与预测流量的差值来判断目标节点的恶意性,并据此做出路由调整。实验结果表明,该系统具有较高的检测率和较低的误警率。Ad hoc networks have the characteristics of wireless transmission medium, dynamic topology, lack of supervision and so on. To solve the problem of security and defense, an intrusion detection system in Ad hoc networks based on network traffic prediction is proposed and implemented. The system composed by nodes detection and response system. Network nodes use detection engine and predict network traffic. This detection engine judges the malicious nodes based on the flow difference of actual and forecast traffic. Thus this system makes routing adjustments based on the nodes detection. The experimental results show that it achieves a higher detection rate and low false positive rate.

关 键 词：ADHOC网络 流量预测 入侵检测 节点检测引擎 响应系统 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]