A New Distributed Intrusion Detection System Model Based on SVM in Wireless Mesh Networks

摘要

Wireless Mesh Networks (WMNs) as a new generation of wireless networking technology have been widely studied and applied in many fields, such as industrial, commercial and public-safety environments. However, due to the open character of wireless communication, it is more vulnerable to external attacks and intrusions. After analyzing the structure and characteristics of WMNs, this paper proposed an distributed intrusion detection system model based on support vector machine in wireless mesh networks, aims to resolved the existing wireless networks intrusion detection method long training time and low detection accuracy problems. And introducing the genetic algorithm to optimize the parameters of Support Vector Machine (SVM). Experimental results show that the algorithm not only significantly reduce the sample training time but also improve the detecting accuracy of every intrusions. Ultimately meet the intrusion detection need of WMNs.