Abstract

With the growing utilization of Internet resources, cyber attackers employ various methods to target network services, including unauthorized access, security breaches, and system misuse. Consequently, network security has become an indispensable component of network systems. To identify such attacks efficiently and effectively, an Intrusion Detection System (IDS) is necessary. Sandeep Gurung et al. (2019) [1] attempted to develop a system using deep learning techniques for intrusion detection, which not only learns from known patterns but also adapts to previously undefined patterns. In their research, two machine learning algorithms, Gaussian Naïve Bayes (GNB) and Decision Tree (DT), were employed for data classification. The NSL-KDD dataset served as the training and testing dataset for these machine learning models. The performance of the proposed model was assessed using two randomly selected feature subsets from the NSL-KDD dataset. The training and testing results for the Decision Tree and Naïve Bayes algorithms were 99.90% and 90.11%, and 98.63% and 85.53%, respectively.

Authors: Dorcas B. Oluwasanmi, Olaniyi. A. Ayeni

Published in: International Conference for Internet Technology and Secured Transactions (ICITST-2023)

  • Date of Conference: 13-15 November 2023
  • DOI: 10.20533/ICITST.2023.0011
  • ISBN: 978-1-913572-63-1
  • Conference Location: St Anne’s College, Oxford University, UK

0