Effective intrusion detection approach with ant colony optimization based feature selection and XgBoost classifier

Secure data communication over the internet and any other network is always at risk; therefore, the intrusion detection system has become a necessary component of computer network systems. Hence, this paper proposes intrusion detection with dimensionality-reduced features, ant colony optimization-based feature selection, and Extreme Gradient Boost (XG-Boost) classifier. For better performance, the proposed system uses the NSL-KDD dataset along with dataset preprocessing. The dimensionality reduction is accomplished using principal component analysis (PCA), and the feature selection is performed using Ant Colony Optimization (ACO). Then, the classification is performed with the Extreme Gradient Boost Algorithm (XG-Boost). The efficiency of the proposed system is evaluated using performance metrics such as F1-score, precision, specificity, accuracy, and recall. Therefore, the obtained results showed 97.6% precision, 97.85% accuracy, 97.88% F1-score, 99.64% specificity, and 97.56% recall.