摘要
针对当前入侵检测系统(intrusion detection system,IDS)中存在的检测准确率低、建模时间长及收敛速度慢等问题,提出一种基于改进鸽群优化算法的入侵检测系统特征选择方法.该方法采用鸽群优化算法对数据中的不相关特征进行优化,通过考虑真阳性率(true positive rate,TPR)、假阳性率(false positive rate,FPR)和特征个数3个指标来选择特征的最佳子集.实验结果表明:相较于现有的特征选择算法,本文算法更具优势,在保证高检测率、低误报率的前提下,减少构建鲁棒IDS所需的特征数目.
Aiming at the problems of low detection accuracy,long modeling time,and slow convergence in the current Intrusion Detection System(IDS),a method of feature selection for intrusion detection system based on modified pigeon-inspired optimization algorithm has been proposed.In this method,pigeon-inspired optimization algorithm is used to optimize the uncorrelated features in the data,and to select the best subset of the features by considering the three indicators of true positive rate(TPR),false positive rate(FPR)and the number of features.The experimental results show that,compared with the existing feature selection algorithms,the proposed algorithm has more advantages,and it can reduce the number of features required to build a robust IDS while ensuring a high detection rate and a low false alarm rate.
作者
吴锋
WU Feng(College of Information Engineering, Xinyang Agriculture and Forestry University, Xinyang Henan 464000, China)
出处
《西南师范大学学报（自然科学版）》
CAS
2021年第5期140-146,共7页
Journal of Southwest China Normal University(Natural Science Edition)
基金
河南省科技攻关项目(172102210450)
信阳农林学院青年教师基金项目(2018LG015).
关键词
特征选择
入侵检测系统
鸽群优化算法
余弦相似性
feature selection
intrusion detection system
pigeon-inspired optimization algorithm
Cosine similarity
