摘要
提出一种基于蚁群-粗糙集原理的入侵检测方法。首先通过粗糙集对不确性数据进行筛选;再利用改进蚁群算法对数据进行约简,减少了计算时间;然后再根据设定的阀值,用蚁群-粗糙集导出规则得到检测结果。实验结果表明,改进蚁群算法数据约简速度高于利用遗传算法以及蚁群算法,该方法对DoS和Probe攻击具有很高的检测率和较低的误检率,并且对U2R和R2L攻击也有较好的检测率。
An intrusion detection method based on ant colony-rough set theory was proposed.The uncertain data was screened by rough set,and then the modified ant colony algorithm was used for data reduction to reduce the computation time.Finally,rules were exported by ant colony-rough set and detection results were got according to the set threshold.Experimental results show that the data reduction rate with improved ant colony algorithm is higher than genetic algorithm and ant colony algorithm.It has high detection rate and low false detection rate for the DoS and Probe attacks and,also has a better detection rate for U2R and R2L attacks.
出处
《化工自动化及仪表》
CAS
北大核心
2010年第9期93-95,99,共4页
Control and Instruments in Chemical Industry
基金
河南省科技计划重点项目(102102210191)
河南省教育厅自然科学研究资助计划项目(2009A520013)
关键词
粗糙集
蚁群算法
入侵检测
属性约简
rough set
ant colony algorithm
intrusion detection
attribute reduction