Intrusion Detection of Imbalanced Network Traffic Based on ML and DL

We develop a Network Intrusion Detection System (NIDS), which uses a suite of machine learning techniques to automatically detect attacks against computer networks and systems. It uses an approach to develop efficient NIDS by using the principal component analysis (PCA) along with different classification algorithms like Support Vector Machines, Random Forest and XgBoost. The purpose of an intrusion detection system is to detect attacks. However, it is equally important to detect attacks at an early stage in order to minimize their impact.

Keywords: Supervised Learning, Anomaly Detection, Intrusion Detection, Principal Component Analysis, Ensemble methods, Bagging and Boosting.