Network Intrusion Detection with XGBoost and Deep Learning Algorithms: An Evaluation Study

Abstract

This paper introduces an effective Network Intrusion Detection Systems (NIDS) framework that deploys incremental statistical damping features of the packets along with state-of- the-art machine/deep learning algorithms to detect malicious patterns. A comprehensive evaluation study is conducted between eXtreme Gradient Boosting (XGBoost) and Artificial Neural Networks (ANN) where feature selection and/or feature dimensionality reduction techniques such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are also integrated into the models to decrease the system complexity for achieving fast responses. Several experimental runs confirm how powerful machine/deep learning algorithms are for intrusion detection on known attacks when combined with the appropriate features extracted. To investigate unknown attacks, the models were trained on a subset of the attack datasets, while a different set (with a different attack type) was kept aside for testing. The decent results achieved further support the belief that through supervised learning, the model could additionally detect unknown attacks.