• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2010, Vol. 32 ›› Issue (9): 27-30.doi: 10.3969/j.issn.1007130X.2010.

• 论文 • 上一篇    下一篇

基于Markov的无线传感器网络入侵检测机制

韩志杰1,张玮玮2,陈志国1   

  1. (1.河南大学计算机与信息工程学院,河南 开封 475004;2.安阳工学院电子信息与电气工程系,河南 安阳 455000)
  • 收稿日期:2010-03-05 修回日期:2010-06-08 出版日期:2010-09-02 发布日期:2010-09-02
  • 通讯作者: 韩志杰
  • 作者简介:韩志杰(1979),男,河南鹿邑人,博士,副教授,研究方向为计算机网络和无线传感器网络。

A MarkovBased Intrution Detection Scheme for Wireless Sensor Networks

HAN Zhijie1,ZHANG Weiwei2,CHEN Zhiguo1   

  1. (1. School of Computer and Information Engineering,Henan University,Kaifeng 475004;
    2. Department of Electronic Information and Electrical Engineering,Anyang Institute of Technology,Anyang 455000,China)
  • Received:2010-03-05 Revised:2010-06-08 Online:2010-09-02 Published:2010-09-02

摘要:

本文采用Markov线性预测模型,为无线传感器网络设计了一种基于流量预测的拒绝服务攻击检测方案——MPDD。在该方案中,每个节点基于流量预测判断和检测异常网络流量,无需特殊的硬件支持和节点之间的合作;提出了一种报警评估机制,有效提高方案的检测准确度,减少了预测误差或信道误码所带来的误报。仿真实验结果表明,Markov模型具有较高的预测精度,能够实时地预测传感器网络流量;MPDD方案能够快速、有效地检测拒绝服务攻击且消耗资源较少。

关键词: 无线传感器网络, 入侵检测, 马尔可夫模型, DoS攻击

Abstract:

In this paper,the authors propose a lightweight denial of service (DoS) attacks detection scheme based on  a simple and efficient Markov traffic prediction model,MPDD (Markov Prediction based DoS attack Detection). In MPDD,each node detects independently Through predicting the traffic of Wireless Sensor Network,which neither special hardware nor node’s cooperation .An algorithm evaluating the reliability of alert is proposed to reduce the false alerts caused by prediction or channel errors. Simulation results has shown that the Markov model can predict sensor network traffic precisely; MPDD is an efficient DoS attacks detection scheme which can quickly detect various DoS attacks with less resource overhead.

Key words: wireless sensor networks;intrusion detection;Markov model;DoS attacks