Intrusion Detection system (IDs) has become the main research focus in the area of information security. Most of the existing IDs use all the features in the network packet to evaluate and look for known intrusive patterns. Some of these features are irrelevant and redundant. The drawback of this approach is a lengthy detection process and degrading performance of an ID system. In this paper a new hybrid algorithm RSNNA (Rough Set Neural Network Algorithm) is used to significantly reduce a number of computer resources, both memory and CPU time, required to detect an attack. The algorithm uses Rough Set theory in order to select out feature reducts and a trained artificial neural network to identify any kind of new attaches. Tests and comparison are done on KDD-99 data set used for The Third International Knowledge Discovery and Data Mining Tools Competition, which was held in conjunction with KDD-99 The Fifth International Conference on Knowledge Discovery and Data Mining, The results showed that the proposed model gives better and robust representation of data as it was able to select features resulting in a 83% data reduction and 85%-90%time reduction and approximately 90%reduction in error in detecting new attacks.

Rough Set theory, feature selection, intrusion detection, dimensionality reduction