基于自适应进化神经网络算法的入侵检测

针对目前多数入侵检测系统的低检测率问题，提出一种自适应进化神经网络算法AENNA。基于遗传算法和BP神经网络算法，利用模拟退火算法的概率突跳和局部搜索强的特性对遗传算法进行改进，采用双种群策略的遗传进化规则实现BP神经网络权值和结构的双重优化；通过对遗传算法的交叉算子与变异算子的改进，设计一种自适应的神经网络训练方法。实验结果表明，基于AENNA的入侵检测方法能够有效提高系统的检测率并降低误报率。

Intrusion detection based on the adaptive evolutionary neural network algorithm

Aiming at the problem of low detection rate existed in current intrusion detection systems,an adaptive evolutionary neural network algorithm (AENNA) based on the genetic algorithm and the BP algorithm is proposed.Firstly,considering the characteristic of probabilistic jumping property and local search ability in the simulated annealing algorithm,the genetic algorithm is improved.Secondly, using the dual population evolution rule,the algorithm optimizes the weight and the network structure of the BP neural network simultaneously.An adaptive neural network training method is designed through improving the crossover operator and mutation operator of the genetic algorithm.Experimental results show that the AENNA based intrusion detection method can effectively improve the detection rate and reduce the false positive rate.