In order to improve the accuracy of network intrusion detection and guarantee the network security, this paper put forward an intelligent intrusion detection system based on expert system and neural network. Firstly, known intrusions were detected by expert system, and then unknown network intrusions were detected by using neural network of expert system, and neural network test results update the expert system rule. The network intrusion detection system was tested with KDD director 99, and the results show that the intelligent intrusion detection systems improve the accuracy of network intrusion detection and reduce the network intrusion misstatement and fail rate of network intrusions , which provides an effective testing tool for network intrusions.%研究网络安全问题,网络入侵方式具有多样性和不确定性,当前大多数人侵检测系统检测正确率低,误报和漏报率高的缺陷.为了提高网络入侵检测正确率,保证网络安全,提出一种基于专家系统和神经网络的智能人侵检测系统.首先采用专家系统对已知网络入侵进行检测,然后采用神经网络对专家系统不能发现的未知网络入侵进行检测,最后利用神经网络检测结果对专家系统规则库进行更新.采用网络入侵检测数据库KDD CUP 99进行仿真,结果表明,智能入侵检测系统提高了网络入侵检测的正确率,有效降低了网络入侵的误报率和漏报率,为网络入侵提供了一种新的有效的检测工具.
展开▼