Abstract: Considering wireless sensor network for intruders to move on multiple nodes and hide the source of the attacks, a distributed intrusion detection model based on ant colony optimization is proposed for wireless sensor networks. The drawback of the existing intrusion detection for unknown attack detection rate and false-positive rate is analyzed. A distributed intrusion detection architecture is put forward and designed based on ant colony optimization algorithm for intrusion detection. Simulation results show that the proposed scheme can improve the intrusion detection accuracy rate of the unknown attack, and reduce the false-positive rate of normal network traffic, solve the problem of routing attacks and Sinkhole attacks, as well as reduce energy consumption for intrusion detection in wireless sensor networks.

Key words: Wireless Sensor Networks, distributed intrusion detection, ant colony optimization, routing attack, Sinkhole attack

摘要： 针对无线传感器网络中入侵者能在多个节点上移动并隐藏攻击源头的特点，提出了一种基于蚁群优化的无线传感器网络分布式入侵检测模型。分析了现有入侵检测对未知攻击检测率和误报率方面的不足，在此基础上提出了分布式入侵检测的体系结构，设计了基于蚁群优化的入侵检测算法。仿真实验表明提出的方案能够提高无线传感器网络对未知攻击的检测率和降低对正常网络流量的误报率，较好地解决了路由攻击、Sinkhole攻击问题，能够降低入侵检测的能耗。

关键词: 无线传感器网络, 分布式入侵检测, 蚁群优化, 路由攻击, Sinkhole攻击