Comprehensive Study: Machine Learning and Deep Learning Approaches in Intrusion Detection Systems

  • Najoua Azizi Computer, Networks, Mobility and Modeling Laboratory, Faculty of Science and Technology Hassan 1st University, Settat, Morocco; National School of Applied Sciences of Berrechid (ENSA), Settat, Morocco
  • Abdellah Jamali Computer, Networks, Mobility and Modeling Laboratory-Faculty of Science and Technology Hassan 1st University, Settat, Morocco; National School of Applied Sciences of Berrechid (ENSA), Settat, Morocco
  • Najib Naja Department of Mathematics, Computer Science and Networking Institut National des Postes et Télécommunications (INPT), Rabat, Morocco
DOI: https://doi.org/10.19139/soic-2310-5070-2782
Keywords: IoT, Cyber-attacks, ML, DL, Fault tolerance, IDS, Cybersecurity, Intrusion Detection, Prevention Mechanisms, Advanced Algorithms, Performance Metrics, Hybrid Models, Vulnerability Detection

Abstract

This paper presents a synthesis of approaches from various studies aimed at enhancing attack classification using machine learning (ML) and deep learning (DL) models. The works studied cover diverse aspects of cybersecurity, with a particular focus on intrusion detection systems (IDS) and Internet of Things (IoT) security. The paper provides an overview of the datasets used to train ML and DL models, the metrics used to evaluate the performance of these techniques, outlines the process for implementing them, and discusses perspectives and future research directions.
Published
2026-01-04
How to Cite
Azizi, N., Jamali, A., & Naja, N. (2026). Comprehensive Study: Machine Learning and Deep Learning Approaches in Intrusion Detection Systems. Statistics, Optimization & Information Computing. https://doi.org/10.19139/soic-2310-5070-2782
Issue
Online First
Section
ICCSAI'24
Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).