Multi-population Diversity-guided Genetic Algorithm for Feature Selection in Network Intrusion Detection
It addresses the problem of maintaining population diversity and guiding evolutionary operators in genetic algorithm-based feature selection for network intrusion detection, but the improvement is incremental over existing multi-population methods.
The paper proposes a Multi-Population Diversity-Guided Genetic Algorithm (MPDGGA) for feature selection in network intrusion detection, achieving the highest accuracy on 10 out of 11 datasets and selecting at least 2.26% of features.
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.