Investigating the Impact of Feature Reduction Through Information Gain and Correlation on the Performance of Error Back Propagation Based IDS

Research in the field of IDS has been going on since long time; however, there exists a number of ways to further improve the efficiency of IDS. This paper investigates the performance of Intrusion detection system using feature reduction and EBPA. The first step involves the reduction in number of features, based on the combination of information gain and correlation. In the next step, error back propagation algorithm (EBPA) is used to train the network and then analyze the performance. EBPA is commonly used due to its ease of use, high accuracy and efficiency. The proposed model is tested over the KDD Cup 99 and NSL-KDD datasets. Results show that the proposed IDS model with reduced feature set outperforms the other models, both in terms of performance metrics and processing time.