论文部分内容阅读
针对现有入侵检测算法中存在着对不同类型攻击检测的不均衡性以及冗余或无用特征导致的检测模型复杂与检测精度下降的问题,提出了一种基于改进多目标遗传算法的入侵检测集成方法.利用改进的多目标遗传算法生成检测率与误报率均衡优化的最优特征子集的集合,并采用选择性集成方法挑选精确的、具有多样性的基分类器构造集成入侵检测模型.实验结果表明,该算法能够有效地解决入侵检测中存在的特征选择问题,并在保证较高检测精度的基础上,对不同类型的攻击检测具有良好的均衡性.
In order to solve the problem that existing intrusion detection algorithms have different detection types of different types of attacks and complicated or unreliable detection models caused by redundant or unwanted features, an intrusion detection and integration based on improved multi-objective genetic algorithm Methods The improved multi-objective genetic algorithm is used to generate a set of optimal feature subsets optimized and balanced by detection rate and false alarm rate, and an integrated intrusion detection model is constructed by using the selective integration method to select accurate and diversified base classifiers. Experimental results show that this algorithm can effectively solve the problem of feature selection in intrusion detection, and has good balance of different types of attack detection based on ensuring high detection accuracy.