A Feature Selection Technique for Intrusion Detection System Based on Iwd and Aco

Abstract

Rapid advancements in the internet technology and its vulnerabilities have led researchers to devise intelligent systems that can provide network security. Intrusion detection systems (IDS) scrutinize all the features to detect intrusive data. Some of the features may be redundant or irrelevant to the detection process, which results in computational complexities and increased training time. To mitigate this problem, a process known as feature selection is used to remove the redundant and irrelevant attributes of the dataset. This paper proposes an intelligent hybrid technique for the purpose of feature selection of KDD CUP'99 dataset using the concepts of metaheuristic optimization. This hybrid approach combines the concepts of Intelligent Water Drops(IWD) and Ant Colony Optimization(ACO)to select features from data. The objective of this work is to optimize the process of feature selection in order to achieve optimal feature subset and reduce the training time.