摘要
为解决网络入侵检测系统中检测算法分类精度不高训练样本数需要较多以及训练学习时间较长等问题,在基于支持向量机的基础上,提出一种新的利用隐空间支持向量机设计IDS的检测算法。仿真实验结果表明本算法较基于支持向量机的检测算法具有更良好的泛化性能,更快的迭代速度,更高的检测精度和更低的误报率。
Detection algorithm in network intrusion detection system has problems of low classification precision, high number of training data set and long training and learning time, etc. To resolve them, based on Support Vector Machines （SVMs） a new detection algorithm using Hidden Space Support Vector Machines （HSSVMs） to design IDS was proposed. The emulation experimental results using KDD CUP 1999 data set show that the new algorithm has better generalization ability, quicker iterative speed, higher detection accuracy, and lower error rate than the one based on SVMs.
出处
《计算机应用与软件》
CSCD
北大核心
2008年第10期87-89,共3页
Computer Applications and Software
基金
江苏省教育厅资助项目(2005-290)
江苏省教科院资助项目(2005-R-196)
关键词
网络安全
入侵检测
隐空间支持向量机
算法设计
Network security Intrusion detection Hidden space support vector machines （HSSVMs） Algorithm design
