Method of Choosing Optimal Features Used to Intrusion Detection System in Ad Hoc Network based on Immunity Algorithm

摘要

In order to improve the detection rate of new intruders in Ad Hoc Network > a new method of intrusion detection system (IDS) based on immune algorithm and back propagation neural network (BPNN) is developed in the paper, on the base of analysis on the network data. In this method, immune algorithm (IA) is used to preprocess the network data, extract key features and reduce dimensions of network data set by feature analysis, then BPNN is adopted to classify the data (program) and recognize intruders. Experimental results show that the method is feasible and efficient, and the detection right rate of intruders in Ad Hoc Network was above 97%.