模糊推理结合Michigan型遗传算法的网络入侵检测方案

A network intrusion detection schemer based on fuzzy inference and Michigan genetic algorithm

针对计算机网络中安全性问题,提出一种融合模糊推理和Michigan型遗传算法的网络入侵检测方案。首先,通过一种启发式过程来确定每个模糊if-then规则后件类和确定性分数。然后,利用Michigan型遗传算法,通过交叉和变异操作来进化模糊系统的规则,产生高分类率的模糊规则。最后,通过协同进化后的模糊系统实现入侵检测。在DARPA数据集上进行实验,结果表明该方案能够精确的检测U2R、R2L、Do S和PRB类网络攻击,具有很高的安全性。

For the issues that the security problem of computer network, a network intrusion detection schemer base on fuzzy inference and Michigan genetic algorithm is proposed. Firstly, a heuristic procedure is set to determine the consequent class and the certainty score of each fuzzy if-then rule. Then, the rules of fuzzy system are evolved by crossover and mutation operations of the Michigan genetic algorithm, to generate the fuzzy rules of high classification rate. Finally, the intrusion detection is realized by the fuzzy system after cooperative evolved. Experiments on DARPA data sets show that the proposed scheme can accurately detect U2 R, R2 L, Do S and PRB attacks, and has high security.