Title: Naive Bayes and deep learning model for wireless intrusion detection systems

Authors: Hariharan Rajadurai; Usha Devi Gandhi

Addresses: School of Information Technology and Engineering (SITE), VIT University, Vellore, India ' School of Information Technology and Engineering (SITE), VIT University, Vellore, India

Abstract: In recent years, online data is exponentially increasing on day basis and accessing that data un-authentically is a major issue. The intruder or attacker is an individual or team who violates the rules of governess by accessing or modifying the data. To protect the online data, there must be a proper mechanism called intrusion detection system (IDS) to be implemented and followed in a right manner. This paper presents a hybrid model for IDS to detect the various attacks in NSL-KDD dataset. The hybrid model is built with a combination of naive Bayes and deep learning (NB-DL) approaches. The NB-DL is tested with benchmarked datasets, and it has scored high accuracy in detecting the attacks. Nowadays, combining two or more different machine learning techniques is popular as multiple methods performance is averaged or selected the best performance between and so on.

Keywords: intrusion detection system; IDS; machine learning; artificial neural network; ANN; naive Bayes; NSL-KDD dataset.

DOI: 10.1504/IJESMS.2021.115527

International Journal of Engineering Systems Modelling and Simulation, 2021 Vol.12 No.2/3, pp.111 - 119

Received: 31 Mar 2020
Accepted: 08 Sep 2020

Published online: 28 May 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article