基于免疫算法和反向传播神经元网络的无线网络入侵检测研究

摘要

In order to detect in the wireless network system both known and unknown types of intrusions and strengthen the wireless network system security, on the basis of network data analysis and study, an immune algorithm and back propagation neural network based intrusion detection approach is put forward. First of all network data is pre-processed with the immune algorithm, then the processed data or codes are recognized with the back propagation neural network. Experiments show that it is practical and effective to detect new types of intruders by the proposed approach, whose detection accuracy can reach as high as 97%.%为了能够检测到无线网络系统中已知和未知类型的入侵者,提高无线网络系统的安全性,在对网络数据分析和研究的基础上,提出一种基于免疫算法和反向传播神经元网络的入侵检测方法.首先利用免疫算法对网络数据进行预处理,再运用反向传播神经元网络对处理后的数据(程序)进行识别.实验表明用该方法检测无线网络系统中的新型入侵者是可行、有效的,检测入侵者的准确率可达到97%.