Title: Network intrusion detection: systematic evaluation using deep learning

Authors: Kiran Shrimant Kakade; T.J. Nagalakshmi; S. Pradeep; B.R. Tapas Bapu

Addresses: Faculty of Business and Leadership MIT, World Peace University, Pune, India ' Saveetha Institute of Medical and Technical Sciences, Saveetha School of Engineering, Chennai, India ' Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India ' Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India

Abstract: Hackers have always regarded getting information on the health of computer networks to be one of the most significant aspects that they need consider. This may include breaking into databases as well as computer networks that are utilised in defensive systems. As a result, these networks are constantly vulnerable to potentially harmful assaults. This paper provides an assessment technique that is based on a collection of tests, with the goal of measuring the effectiveness of the individual elements of an IDS as well as the influence those components have on the whole system. It evaluates the deep neural network's potential efficacy as a classification for the many kinds of intrusion assaults that may be carried out. Based on the results of the studies, it seems that the level of accuracy achieved by intrusion detection using deep convolutional neural network is satisfactory.

Keywords: machine-learning; networks intrusion detection systems; and networks.

DOI: 10.1504/IJESDF.2024.137042

International Journal of Electronic Security and Digital Forensics, 2024 Vol.16 No.2, pp.190 - 201

Received: 30 Sep 2022
Accepted: 24 Nov 2022
Published online: 01 Mar 2024 *

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