AN APPROACH USING ENSEMBLE CORE VECTOR MACHINES FOR NETWORK IDS

Past many activities carried by common man were manual. Today’s stay connected world there’s huge usage of e-services which made man’s activities online, along with these services security concerns also increased. Many researchers proposed efficient Intrusion Detection systems are in practice; but still hackers manage to attack the systems to intrude. This paper proposes an efficient intrusion detection system using Ensemble Core Vector Machine approach, where algorithms work on the basis of Minimum Enclosing Ball concept. It detects the attacks like: R2L, U2R, Probe and DoS attack. For each type of attack, a CVM classifier is modeled. KDD Cup’99 datasets are used for training and testing the classifiers. This approach uses Chi-square test for selecting the relevant features for each attack and a weighted function is applied to these features for the dimensionality reduction. The test results verify that this model achieves high efficiency in all the four attacks with less computation time compared to the existing approaches.