Intrusion detection based on hybrid metaheuristic feature selection

Abstract The multidimensional features of network flows are the main data source for intrusion detection, but excessively low-value features generate accuracy and efficiency challenges. Researchers have used redundant feature reduction to simplify intrusion detections, and feature selection algorithms are beginning to be widely used. This paper presents a novel hybrid feature selection algorithm, CSA-FPA, which combines both a crow search algorithm and a flower pollination algorithm. In this method, properties such as local pollination and the levy flight of FPA are used to balance the global search and local search efficiencies, and parameters such as group distance and probability thresholds are introduced to customize the model’s appearance. The simulation results on the UNSW-NB15 and CIC-IDS2017 datasets show that the proposed CSA-FPA method achieves better detection accuracies than previous algorithms. Using the proposed feature selection method, the AdaBoost classifier achieved a detection accuracy of 99.14% on the CIC-IDS2017 dataset and 97.98% on the UNSW-NB15 dataset.