Enhancing Network Security: A Comprehensive Review of Deep Learning Models and Datasets for IDS

Padmapani P. Tribhuvan , hCAP Institute of Technology, Chhatrapati Sambhajinagar, MS, India.
Amrapali P. Tribhuvan, Dr. Babasaheb Ambedkar Marathwada University, Chhatrapati Sambhajinagar, MS, India.

Avalokiteshvara Journal of Artificial Intelligence (AJAI)
Volume 1, Issue 1, March 2025, pp. 10-18
Review Article

---

Abstract: Intrusion Detection Systems (IDS) are indispensable in safeguarding computer networks from increasingly diverse cyber threats. Traditional methods, while effective for known attacks, struggle with the detection of novel and sophisticated threats. Deep Learning (DL) models have emerged as promising to enhance IDS capabilities by automatically learning and extracting complex patterns from network data. This paper comprehensively reviews various DL models applied in IDS, examining their applications, datasets, strengths, challenges, and future research directions.

Keywords: Intrusion Detection System, Deep Learning, Convolutional Neural Network, Re-current Neural Network, Generative Adversarial Network, Long Short-Term Memory

📄 Download Full PDF