基于改进蚁群算法与遗传算法组合的网络入侵检测

发布时间：2018-02-03 05:57

本文关键词： 网络入侵遗传算法蚁群优化算法支持向量机　出处：《重庆邮电大学学报(自然科学版)》2017年01期 　论文类型：期刊论文

【摘要】：为提高网络入侵检测的检测效果,提出一种基于改进蚁群算法与遗传算法组合的网络入侵检测方法。该方法采用遗传算法(genetic algorithm,GA)对网络入侵的特征集进行快速选取,为后续特征提取打下基础;对传统蚁群算法(ant colony optimization,ACO)的节点选择策略和信息素更新策略进行改进,提出一种改进的蚁群算法,提高对最优特征的选择效果,采用改进的蚁群算法对特征进一步选择;采用支持向量机(support vector machine,SVM)统计机器学习方法建立各类网络入侵的检测分类器。仿真实验结果表明,新的网络入侵检测方法综合GA和改进蚁群算法的优势,能够获得更好的入侵特征,从检测正确率、误报率和漏报率3个方面综合比较,新的网络入侵检测方法具有更好的网络入侵检测效果,且提高了检测速率。
[Abstract]:In order to improve the detection effect of network intrusion detection. A network intrusion detection method based on the combination of improved ant colony algorithm and genetic algorithm is proposed, in which genetic algorithm is used. GA) is used to select the feature set of network intrusion quickly, which lays the foundation for the subsequent feature extraction. The node selection strategy and pheromone updating strategy of traditional ant colony optimization algorithm (ACO) are improved, and an improved ant colony algorithm is proposed. The improved ant colony algorithm is used to improve the selection effect of the optimal feature. The statistical machine learning method of support vector machine support vector machine is used to establish various kinds of network intrusion detection classifiers. The simulation results show that. The new network intrusion detection method synthesizes the advantages of GA and improved ant colony algorithm, which can obtain better intrusion characteristics. It is compared comprehensively from three aspects: correct detection rate, false alarm rate and false alarm rate. The new network intrusion detection method has better network intrusion detection effect and improves the detection rate.
【作者单位】：西京学院电子信息工程系;
【基金】：国家自然科学基金(61273271) 西京学院科研基金(XJ150122)~~
【分类号】：TP18;TP393.08
【正文快照】： 0引言近年来网络的开放性和虚拟性给网络入侵带来了极大的方便,如蠕虫、网站挂马、拒绝服务攻击、钓鱼和僵尸网络等,针对日益严重的网络入侵活动,入侵检测系统(intrusion detection system,IDS)作为一种积极主动的安全防护技术得到了迅猛的发展[1-3]。为使网络入侵检测技术能

【参考文献】