Unveiling the Landscape of Machine Learning and Deep Learning Methodologies in Network Security: A Comprehensive Literature Review
Nouf Majid Sultan Eid Saeed, Amer Ibrahim, Liaqat Ali, Nidal A. Al-Dmour, Abdul Salam Mohammed, Taher M. Ghazal
Abstract
The dynamic nature of cyber threats offers a continual problem in the field of cybersecurity in the context of the expanding internet environment. This study provides an in-depth assessment of the literature on machine learning (ML) and deep learning (DL) methodologies for network analysis for intrusion detection. This review curates, assesses, and distils method-specific findings while considering temporal or thermal correlations. It provides a recognition of the importance of data in ML and DL approaches, and a comprehensive overview of frequently used network datasets in ML/DL applications, as well as the inherent challenges of adopting ML/DL in the cybersecurity field. The study concludes with well-informed recommendations for future areas of research in this critical domine.