基于Web数据流技术的网络入侵检测研究  

Study on network intrusion detection based on Web data streams technology

作　　者：许颖梅[1] 

机构地区：[1]商丘师范学院计算机系,河南商丘476000

出　　处：《郑州轻工业学院学报（自然科学版）》2012年第3期11-14,共4页Journal of Zhengzhou University of Light Industry:Natural Science

基　　金：河南省科技厅科技攻关项目(112102210210);河南省教育厅自然科学研究计划资助项目(2011A520034)

摘　　要：针对传统多遍扫描数据库的挖掘技术构建的入侵检测模型已不能满足Web数据流高速并且无限到达的需要,根据多维频繁模式的特点,提出了一种新的入侵检测模型和一种新型数据结构SW.Tree,并给出了一种基于滑动窗口树的挖掘频繁项集的新型算法AFP.对不同流量数据的实验结果表明该模型有较高的报警率和较低的误报率.Aiming at the problem that intrusion detection model constructed by mining technique with multiscanning to databases has not met the needs of high-speed and unlimited for Web data streams. Based on the characteristic of multi-dimension frequent patterns, a new intrusion detection model and data structure called SW. Tree was proposed, and a new algorithm AFP mining frequent patterns from data streams based on sliding window tree was designed. The different flow experiments data showed that the model had high alarm rate and low false alarm rate.

关 键 词：Web数据流 网络入侵检测 频繁项集 滑动窗口 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]