A COMPARISON STUDY FOR INTRUSION DATABASE (KDD99, NSL-KDD) BASED ON SELF ORGANIZATION MAP (SOM) ARTIFICIAL NEURAL NETWORK

Detecting anomalous traffic on the internet has remained an issue of concern for the community of security researchers over the years. The advances in the area of computing performance, in terms of processing power and storage, have fostered their ability to host resource-intensive intelligent algorithms, to detect intrusive activity, in a timely manner. As part of this project, we study and analyse the performance of Self Organization Map (SOM) Artificial Neural Network, when implemented as part of an Intrusion Detection System, to detect anomalies on acknowledge Discovery in Databases KDD 99 and NSL-KDD datasets of internet traffic activity simulation. Results obtained are compared and analysed based on several performance metrics, where the detection rate for KDD 99 dataset is 92.37%, while detection rate for NSL-KDD dataset is 75.49%.