基于集成神经网络入侵检测系统的研究与实现

为解决传统入侵检测模型所存在的检测效率低,对未知的入侵行为检测困难等问题,对集成学习进行了研究与探讨,提出一种采用遗传算法的集成神经网络入侵检测模型,阐述了模型的工作原理和各模块的主要功能.模型通过遗传算法寻找那些经过训练后差异较大的神经网络进行集成.实验表明,集成神经网络与检测率最好的单个神经网络相比检测率有所提高.同时,该模型采用机器学习方法,可使系统能动态地适应环境,不仅对已知的入侵具有较好的识别能力,而且能识别未知的入侵行为,从而实现入侵检测的智能化.

Study and Implementation of an Intrusion Detection System Based on Ensemble Learning in Neural Networks

In order to solve the problem of low detection rate for novel attacks and the difficulties in detecting un- known intrusions existing in traditional intrusion systems,the paper conducts the research and discussion of the en- semble learning,proposes a model based on ensemble learning in neural networks using genetic algorithm,and elab- orates the principle of the system and the main function of its various modules.This model selects a group of neural networks using genetic algorithm.Experiments show that using the ensemble learning method,the detection rate is higher than that of using any individual networks.At the same time,by using the machine learning method,this mod- el is adapted to the environment dynamically,so it has a better detection rate not only to the known intrusion,but also to the unknown intrusion,thus realizing an intelligent intrusion detection system.