Performance analysis of intrusion detection system using various neural network classifiers

In recent years, the security has become a critical part of any organizational information systems. The intrusion detection system is an effective approach to deal with the problems of networks using various neural network classifiers. In this paper, the performance of intrusion detection with various neural network classifiers is compared. In the proposed research the three types of classifiers used are Feed Forward Neural Network (FFNN), Probabilistic Neural Network (PNN) and Radial Basis Neural Network (RBNN). In this problem, the feature reduction techniques are used to a given KDD Cup 1999 dataset. The performance of the full featured KDD Cup 1999 dataset is compared with that of the reduced featured KDD Cup 1999 dataset. The MATLAB software is used to train and test the dataset and the efficiency is measured. Using the above said technique, it is proved that the reduced dataset is performing better than the full featured dataset.