Date Added: Dec 2009
The steady growth in research on intrusion detection systems has created a demand for tools and methods to test their effectiveness. Intrusion Detection System (IDS), is based on the belief that an intruder's behaviour will be noticeably different from that of a legitimate user and would exploit security vulnerabilities. This paper proposes a novel intrusion detection approach by applying Generalized Regression Neural Network (GRNN) for feature selection and detection. The MIT's KDD Cup 99 dataset is used to evaluate the present method. The results clearly demonstrate that the method can be an effective way for intrusion feature selection and detection and promises a good scope for further research.