A New Multi-Objective Binary Bat Algorithm for Feature Selection in Intrusion Detection Systems

Abstract

Monitoring network traffic and detecting security threats is a vital task in today's world, and intrusion detection systems (IDS) have become an essential tool for this purpose. However, IDSs have to analyze large volumes of data, which often contain irrelevant and redundant features. This makes the job of IDSs more challenging, as they must sift through all available features to identify attack patterns, leading to longer processing time and reduced detection accuracy. To address this, we propose a new wrapper approach for solving the feature selection (FS) problem. Our proposed approach uses a novel multi-objective binary bat algorithm (MBBA-FS) with a decision tree classifier. The MBBA-FS aims to produce a set of non-dominated solutions that minimize the number of features used while maintaining a high detection accuracy. Then, we use a frequency ranking method to identify a single subset of relevant features from the resulting set of non-dominated solutions. We tested the feasibility and performance of our approach against other leading FS methods using various datasets, including KDD CUP 1999, NLS-KDD, UNSW-NB15, and several synthetic benchmarks. The experimental results show that MBBA-FS outperforms existing FS approaches in terms of classification accuracy and number of selected features.