Optimizing radial basis function networks to recognize network attacks for intrusion detection

A methodology for optimizing radial basis function (RBF) networks is proposed, which consists of the RBF network and the self-organizing map (SOM), aiming at improving the performance of the recognition and classification of novel attacks for intrusion detection. The optimal network architecture of the RBF network is determined automatically by the improved SOM algorithm, in which the centers and the number of hidden neurons are self-adjustable. The intrusion feature vectors are extracted from a benchmark dataset (the KDD-99) designed by DARPA. The experimental results demonstrate that the proposed approach to recognize network attacks performance especially in terms of both efficient and accuracy.