入侵检测数据分类模型—PCANN

Data Classify Model of Intrusion Detection-PCANN

针对现有基于神经网络(NN)的入侵检测模型(IDS)所存在的不足,在分析入侵数据固有的特点的基础上,引入主成分分析方法,提出了一种"主成分分析(PCA)-神经网络"的入侵检测数据分类模型。该模型中入侵数据得以缩减,神经网络规模得以简化,弥补了现有入侵检测模型所存在的不足。基于KDD'99数据的仿真试验,验证了该模型的有效性。

On the basis of analyzing demerits of existing Neural Network-Based IDS Frame and inherent characteristics of Intrusion data, this paper introduces method of PCA and presents a new IDS model based on ＂PCA-NN＂. The model cuts down the dimensions of intrusion data and simplifies the scale of NN, reduce the weakness of modem IDS Framework. Experiment has been done on dataset in KDD＇99 and the result shows that the theory is effective and valid.