Statistical Analysis of Different Artificial Intelligent Techniques applied to Intrusion Detection System

Intrusion detection is the act of detecting unwanted traffic on a network or a device. Several types of Intrusion Detection Systems (IDS) technologies exist due to the variance of network configurations. Each type has advantages and disadvantage in detection, configuration, and cost. In general, the traditional IDS relies on the extensive knowledge of security experts, in particular, on their familiarity with the computer system to be protected. To reduce this dependence, various datamining and machine learning techniques have been used in the literature. The experiments and evaluations of the proposed intrusion detection system are performed with the NSL-KDD intrusion detection dataset. We will apply different learning algorithms on NSL-KDD data set, to recognize between normal and attack connections and compare their performing in different scenariosdiscretization, features selections and algorithm method for classification- using a powerful statistical analysis: ANOVA. In this study, both the accuracy of the configuration of different system and methodologies used, and also the computational time and complexity of the methodologies are analyzed.