A Frame of Intrusion Detection Learning System Utilizing Radial Basis Function

The process of monitoring the events that occur in a computer system or network and analyzing them for signs of intrusion is known as Intrusion Detection System (IDS). Detection ability of most of the IDS are limited to known attack patterns; hence new signatures for novel attacks can be troublesome, time consuming and has high false alarm rate. To achieve this, system was trained and tested with known and unknown patterns with the help of Radial Basis Functions (RBF). KDD 99 IDE (Knowledge Discovery in Databases Intrusion Detection Evaluation) data set was used for training and testing. The IDS is supposed to distinguish normal traffic from intrusions and to classify them into four classes: DoS, probe, R2L and U2R. The dataset is quite unbalanced, with 79% of the traffic belonging to the DoS category, 19% is normal traffic and less than 2% constitute the other three categories. The usefulness of the data set used for experimental evaluation has been demonstrated. The different metrics available for the evaluation of IDS were also introduced. Experimental evaluations were shown that the proposed methods were having the capacity of detecting a significant percentage of rate and new attacks.