Network Intrusion Detection Using Hybrid Machine Learning Model

Abhishek Mazumder, Niton Mohammed Kamruzzaman, Nasrin Akter, Nafija Arbe, Md Mahbubur Rahman

20212021 International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT)24 citationsDOI

Abstract

In this era of network security, Intrusion Detection System plays an important role. It is used to predict network data traffic as normal or anomaly. Several machine learning models are used for building an accurate Intrusion Detection System. In this paper, a hybrid machine learning model with a new feature selection method is proposed for better performance of the Intrusion Detection System. In this proposed model, the Intrusion Detection System is built with a combination of supervised and unsupervised machine learning models. A brief comparison between the proposed model and the other machine learning models such as AdaBoost, XGBoost, Random Forest, Gaussian Naive Bayes, LGB is narrated in this paper. We applied the models on the NSL KDD dataset and experimentally proved that the accuracy level of our proposed model is approximately 11% higher than the others.

Topics & Concepts

Computer scienceIntrusion detection systemMachine learningArtificial intelligenceAdaBoostFeature selectionModel selectionRandom forestNaive Bayes classifierAnomaly detectionAnomaly-based intrusion detection systemData miningSupport vector machineNetwork Security and Intrusion DetectionInternet Traffic Analysis and Secure E-votingAnomaly Detection Techniques and Applications