A Feature Reduction Intrusion Detection System using Genetic Algorithm

Abstract

Nowadays security has become the most important feature in any field. We make use of the Intrusion Detection System (IDS) as it gathers information related to activities that violate security policies. An intrusion detection system (IDS) could be a device or software system application that monitors a network or systems for malicious activity or policy violations. Any malicious activity or violation is usually rumored either to associate administrator or collected centrally employing a security data and event management (SIEM) system. This system first uses the feature ranking on basis of information gain and correlation by ANN classifier. These reduced options are then fed to a feed forward neural network for coaching and testing on KDD99 dataset. This Intrusion detection system have curse of dimensionality which tends to increase time complexity and decrease resource utilization and number of comparisons are high. In order to overcome this we propose the system, which make use of the other feature ranking technique called genetic algorithm. Feature reduction is then done by combining ranks obtained from each data gain and correlation employing a novel approach to spot helpful and useless options. The input is feature set and produce the best output set using genetic algorithm. This system will reduce time complexity, only limited number of comparisons are done and also the performance rate is high in terms of classification accuracy.