一种改进的高维孤立点挖掘入侵检测方法  

Improved Intrusion Detection Method Based on High-dimensional Outlier Mining

作　　者：申利民[1] 孙中魁 陈磊 冯佳音[1] 李志明[1] SHEN Li-min;SUN Zhong-kui;CHEN Lei;FENG Jia-yin;LI Zhi-ming(Yanshan University School of Information Science and Engineering,Qinghuangdao 066004,China;North China University of Science and Technology Qinggong College,Tangshan 063000,China;North China University of Science and Technology Graduate School,Tangshan 063000,China)

机构地区：[1]燕山大学信息科学与工程学院,河北秦皇岛066004 [2]华北理工大学轻工学院电气信息学院,河北唐山063000 [3]华北理工大学研究生院,河北唐山063000

出　　处：《小型微型计算机系统》2020年第12期2636-2640,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61772450)资助;河北省高等学校科技计划重点项目(ZD2018219)资助;河北省科技厅计划项目(15210706)资助。

摘　　要：入侵检测系统中原始数据多为高维数据,针对基于频繁模式高维孤立点挖掘算法不易获取完全频繁模式和时间复杂度高等问题,提出了一种基于最大频繁模式因子的高维孤立点挖掘算法获取孤立点集,并对孤立点集合进行进一步分析获取入侵检测的攻击模式.利用NSL-KDD数据集进行实验,和相关工作对比,结果表明所提出的方法在检测精确度和复杂度都具有优异的表现.Most of the original data in intrusion detection system are high-dimensional data.Aiming at the problems of high-dimensional outlier mining algorithm based on frequent patterns,w hich is not easy to obtain complete frequent patterns and high time complexity,a high-dimensional outlier mining algorithm based on the maximum frequent patterns factor is proposed to obtain the outlier set,and further analyzes the outlier set to obtain the attack pattern of intrusion detection.Experiments are carried out with NSL-KDD data set,compared with other related work,the experiments show that the proposed method has excellent performance in detection accuracy and complexity.

关 键 词：入侵检测 高维数据 孤立点挖掘 最大频繁模式 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]