两种神经网络在入侵检测中的应用

由于入侵检测的数据都是海量高维数据,提出一种基于主成分分析(PCA)的特征提取方法,以提高入侵检测的处理效率。选用Kddcup’99网络连接数据集进行预处理和PCA特征提取后,分别通过BP神经网络和Kohonen神经网络进行训练和测试,分析检测率,误报率,训练时间和检测时间。实验结果表明,基于PCA的BP神经网络能减小入侵检测的运算量,提高入侵检测的识别效果。

Applications of Two Neural Network Algorithms in Intrusion Detection

Due to the massive amount of intrusion data massive,a feature extracting method based on PCA(Principle Component Analysis) is presented in this paper.The Kddcup'99 network is employed to pre-process the data.And based on PCA feature extraction,the extracted data is trained and tested,and the detection rate,false alarm rate,training time and testing time are analysed with BP and Kohonen neural networks.Experiment results indicate that the BP neural network based on PCA can substantially reduce the computatio...