Cutting-edge approaches in intrusion detection systems: a systematic review of deep learning, reinforcement learning, and ensemble techniques.

Kalpani, Nethma; Rodrigo, Nureka; Seneviratne, Dilmi; Ariyadasa, Subhash; Senanayake, Janaka

Abstract

The growing number of networked devices and complex network infrastructures necessitates robust network security measures. Network intrusion detection systems are crucial for identifying and mitigating malicious activities within network environments. Traditional intrusion detection systems (IDS) often struggle to adapt to new and evolving threats. To address these limitations, researchers are increasingly turning to advanced methodologies such as deep learning (DL), reinforcement learning (RL), and ensemble learning (EL), which offer enhanced capabilities in detecting sophisticated and previously unseen attacks. This systematic literature review (SLR) evaluates 33 technical studies from 2020 to 2024 on the application of DL, RL, and EL in IDS. The study reviews the DL and RL methods used in IDS, along with detection methods that employ EL techniques, to combine the strengths of these approaches. It highlights the advantages, disadvantages, and applicability of the proposed techniques, while also suggesting potential improvements. The aim of this SLR is to provide researchers and practitioners with a comprehensive understanding of current IDS methodologies leveraging DL, RL, and EL, enabling the development of more effective and resilient network security solutions. In addition, this review identifies gaps in the existing literature and outlines potential future research directions.

Citation

KALPANI, N., RODRIGO, N., SENEVIRATNE, D., ARIYADASA, S. and SENANAYAKE, J. 2025. Cutting-edge approaches in intrusion detection systems: a systematic review of deep learning, reinforcement learning, and ensemble techniques. Iran journal of computer science [online], Online First. Available from: https://doi.org/10.1007/s42044-025-00246-8

• Journal Article Type: Review
• Acceptance Date: Feb 22, 2025
• Online Publication Date: Mar 5, 2025
• Deposit Date: Mar 20, 2025
• Publicly Available Date: Mar 6, 2026
• Journal: Iran Journal of computer science
• Print ISSN: 2520-8438
• Electronic ISSN: 2520-8446
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1007/s42044-025-00246-8
• Keywords: Intrusion detection systems; Deep learning; Reinforcement learning; Ensemble learning; Network security
• Public URL: https://rgu-repository.worktribe.com/output/2755672