基于多神经网络的入侵检测系统模型研究

为了进一步提高入侵检测系统的检测性能,提出一种新型的基于多神经网络的入侵检测系统模型IDSMN.该模型引入多神经网络和模糊理论,基本思想是将网络数据集分成不同类型的子集,在不同子集上训练形成不同的子神经网络,然后用模糊理论进行多神经网络非线性融合,形成最优判断.

Research on model of Intrusion Detection System based on multi-neural network

In order to improve the detection performance of Intrusion Detection System, it was presented a new model of Intrusion Detection System based on multi-neural network. The multi-neural network and fuzzy integral were used in the model. The basic idea was to divide network dataset into several sub-datasets according to different data attributes, train on different sub-datasets and construct different sub-neural networks separatelyf-then nonlinearly combine the results from multiple sub-neural networks by fuzzy integral, at last the System would determine class.