摘要
无线传感器网络与传统网络存在较大差异,传统入侵检测技术不能有效地应用于无线传感器网络。结合无线传感器网络的特点,提出一种基于统计异常的入侵检测。入侵检测为传感器节点在正常工作状态下的某些系统特征建立行为模式,并通过统计观测值对正常行为模式的偏离程度来判断是否存在入侵。理论分析及仿真实验表明,提出的入侵检测技术可有效检测入侵,检测算法简洁高效,利于节能,适用于供能紧张的无线传感器网络。
Wireless sensor networks are different from traditional networks, so traditional intrusion detection cannot be applied efficiently to them. According to the characteristics of wirelss sensor networks, the paper presents a intrusion detection based on statistic anomaly in wireless sensor networks. This intrusion detection establishs models for some system characteristics in normal state of the sensor nodes, and detects the intrusion through the deviation degree of observed values to normal model. Theory and simulation results indicate that the proposed intrusion detection can detect intrusion effectively, and its algorithm is highly efficient for the energy conservation to fit demand of enegy restriction in wireless sensor networks.
出处
《火力与指挥控制》
CSCD
北大核心
2009年第7期129-132,共4页
Fire Control & Command Control
基金
中南林业科技大学青年科学基金资助项目(2008031B)
关键词
无线传感器网络
入侵检测
统计异常
wireless sensor networks ,intrusion detection ,statistic anomaly