A Review of Generative Adversarial Networks for Intrusion Detection Systems: Advances, Challenges, and Future Directions

Abstract

The ever-growing network traffic threat landscape necessitates adopting accurate and robust intrusion detection systems (IDSs). IDSs have become a research hotspot and have seen remarkable performance improvements. Generative adversarial networks (GANs) have also garnered increasing research interest recently due to their remarkable ability to generate data. This paper investigates the application of (GANs) in (IDS) and explores their current use within this research field. We delve into the adoption of GANs within signature-based, anomaly-based, and hybrid IDSs, focusing on their objectives, methodologies, and advantages. Overall, GANs have been widely employed, mainly focused on solving the class imbalance issue by generating realistic attack samples. While GANs have shown significant potential in addressing the class imbalance issue, there are still open opportunities and challenges to be addressed. Little attention has been paid to their applicability in distributed and decentralized domains, such as IoT networks. Efficiency and scalability have been mostly overlooked, and thus, future works must aim at addressing these gaps.