Optimizing intrusion detection using intelligent feature selection with Gray wolf-based FOX algorithm

Abstract

Intrusion Detection Systems (IDS) are crucial in protecting computer networks against malicious activities. However, the performance of IDS can be improved by selecting the most relevant features from the vast amount of network traffic data. This article proposes an innovative approach to optimizing intrusion detection using intelligent feature selection with the FOX algorithm based on Grey Wolf optimization. In this study, intrusion detection is conducted using the KDDCup99 database. Then, processed features are selected. After preprocessing and preparing the dataset for data mining, they are fed into an MLP neural network. Each of the features and findings play a significant role in intrusion detection and prediction. In other words, not all features are equally valuable. Determining the value and role of each feature in intrusion detection is crucial. In this study, the value and role of each of these features are optimized and intrusion is identified by the Grey Wolf Optimization (GWO) algorithm. The proposed method's suitable accuracy compared to other classification algorithms used in this research such as Support Vector Machines and Decision Trees, demonstrates the efficiency and superiority of the proposed method.