基于LVQ算法的SOM神经网络在入侵检测系统中的应用  

Application of SOM Neural Networks Based on LVQ in Intrusion Detection

作　　者：周豫苹 郑荔萍[1] 

机构地区：[1]漳州师范学院计算机科学与工程系,福建漳州363000

出　　处：《电脑与信息技术》2009年第6期1-3,共3页Computer and Information Technology

基　　金：国家自然科学基金资助项目(60674088)

摘　　要：目前,入侵检测技术(IDS)已成为网络安全领域研究的焦点,神经网络被应用到这项技术的研究上,文章在建立一类基于SOM神经网络的分类器的基础上,应用了LVQ算法对SOM进行二次监督学习训练,极大提高了分类器的检测性能。仿真试验结果证明了该检测模型的有效性。Intrusion detection technique has become the focus in the area of network security research. Neural Networks approaches have been applied to the intrusion detection field. This paper firstly construct one classifier based on SOM neural networks, then an application of the LVQ algorithm after SOM training improves classification performance in this domairn Finally a publicly available DRAPA/KDD99 dataset is used to demonstrate the approaches and the results show their accuracy.

关 键 词：自组织特征映射 入侵检测 神经网络 学习矢量量化 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]