Multi-population Diversity-guided Genetic Algorithm for Feature Selection in Network Intrusion Detection

TL;DR

This paper introduces MPDGGA, a novel multi-population genetic algorithm guided by diversity measures, to improve feature selection for network intrusion detection, outperforming existing methods.

Contribution

The study proposes a new diversity-guided multi-population genetic algorithm tailored for feature selection in intrusion detection systems.

Findings

Achieves highest accuracy on 10 out of 11 datasets.

Selects at least 2.26% of features.

Significantly outperforms four other models.

Abstract

Network Intrusion Detection System is a critical means of ensuring cybersecurity. However, existing Genetic Algorithm-based feature selection methods face several limitations when dealing with high-dimensional redundant traffic features. For example, population diversity is difficult to maintain, and evolutionary operators lack guidance. To solve these problems, this study proposes the Multi-Population Diversity-Guided Genetic Algorithm (MPDGGA). First, we build a chained multi-population evolutionary structure. Second, we introduce a diversity-guided operator based on information gain ratio. Experiments on NSL-KDD, UNSW-NB15, and 9 UCI datasets show that the proposed model significantly outperforms four other advanced multi-population feature selection models. Across the 11 datasets, it attains the highest accuracy on 10 datasets and at least 2.26% of the features were selected.