一种基于RBM-SVM算法的无线传感网络入侵检测算法

AN INTRUSION DETECTION ALGORITHM FOR WIRELESS SENSOR NETWORK BASED ON RBM-SVM ALGORITHM

针对以通信节点为基础的无线传感器网络作为物联网基础设施开始临越来越多的信息安全威胁,提出一种基于RBM特征提取和多层SVM检测的无线传感网络入侵检测方法,将收集到的高维网络数据进行特征信息提取并结合网络拓扑结构及攻击流量相似性分层检测入侵行为。实验仿真采用NSL_KDD公共入侵检测数据集,实验结果表明该模型对网络流量检测准确率为99.06%。

As the infrastructure of the Internet of things,wireless sensor networks based on communication nodes are facing more and more information security threats.This paper proposes an intrusion detection algorithm for wireless sensor network based on RBM feature extraction and multi-layer SVM detection.The collected high-dimensional network data was used to extract feature information.Combing with the network topology and attack traffic similarity,the algorithm detected intrusion behaviors in layers.The experimental simulation in this paper was carried out on the NSL_KDD intrusion detection data set.The experimental results show that the accuracy of the model is 99.06%for network traffic detection.