摘要
由于许多重要的无线传感器网络需要一个高效、轻量级、灵活的入侵检测算法来检测恶意节点,提出了一种基于二叉树的SVM多类分类方法的合作型入侵检测方案。该方案可扩展性较好,有效地节省了传感器节点的能量。仿真实验表明,与已经提出的入侵检测系统相比,该方案具有较低的误报率和较高的检测率。
Due to many critical wireless sensor networks require an efficient,lightweight and flexible intrusion detection algorithm to identify malicious attackers,this paper proposed SVM-based cooperation intrusion detection scheme.The scheme has a good expansibility and effectively saves the energy of sensor nodes.Simulation results show that the scheme has a low false alarm rate and a higher detection rate compared with existing intrusion detection schemes.
出处
《计算机应用研究》
CSCD
北大核心
2010年第4期1489-1492,共4页
Application Research of Computers
基金
国家"211工程"建设项目(181070H901)
江苏省自然科学基金资助项目(2003101SBRB231)
关键词
无线传感器网络
入侵检测
支持向量机
二叉树多类分类方法
误报率
检测率
wireless sensor networks(WSN)
intrusion detection
support vector machine(SVM)
binary tree multi-class classification method
false alarm
detection accuracy