改进蚁群算法优化支持向量机的网络入侵检测  

Network Intrusion Detection Model Based on Support Vector Machine and Improved and Colony Optimiza Tion Algorithm

作　　者：王雪松[1] 梁昔明[2] 

机构地区：[1]佛山职业技术学院电子信息系,广东佛山528137 [2]北京建筑工程学院理学院,北京100044

出　　处：《计算技术与自动化》2015年第2期95-99,共5页Computing Technology and Automation

基　　金：国家自然科学基金资助项目(60874070);广东省教育厅项目(2010tjk446)

摘　　要：针对支持向量机参数优化问题,为了提高网络入侵检测率,提出一种变异蚁群算法优化支持向量机的网络入侵检测模型(MACO-SVM)。首先采用蚁群搜索路径节点代表支持向量机参数,并将网络入侵检测率为目标函数,然后通过蚁群算法的全局寻优能力和反馈机制寻找最优参数,并对蚂蚁进行高斯变异,克服蚁群陷入局部极值,最后将最优路径上的节点连接起来得到SVM的最优参数,建立最优网络入侵检测模型。采用KDD99数据集对模型进行仿真实验,仿真结果表明,MACO-SVM的网络入侵检测速度要快于其它网络入侵检测模型,而且提高了网络入侵检测率。In order to solve parameters optimization problem for support vector machine in network intrusion detection,this paper proposed a network intrusion detection model based on support vector machine,whose parameters were optimized by the improved ant colony optimization algorithm.Firstly,the node of ant colony search path represented the parameters of support vector machine,network intrusion detection rate was taken as the goal function,and then global optimization and feedback mechanism of ant colony optimization algorithm were used to find the optimal path,and Gauss mutation was introduced to overcome local minima,and the nodes of the optimal path were connected to form the optimal parameters of support vector machine and to establish the optimal network intrusion detection model,and the simulation experiments were carried out on the KDD99 dataset.The simulation results show that the proposed model not only accelerates network intrusion detection rate,but also improves intrusion detection rate,compared with reference models.

关 键 词：网络入侵 蚁群优化算法 支持向量机 参数优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]