A Hybrid Approach to Improve the Intrusion Detection Systems Using Generative Artificial Intelligence and Deep Reinforcement Learning

Ines Ben Makhlouf, Ghassen Kilani, Fehmi Jaafar, Haïfa Nakouri, Haïfa Nakouri

2025

Abstract

In recent years, Artificial Intelligence (AI)-based tools have gained widespread adoption as AI-powered prompts have become increasingly sophisticated. As a result, the rise of AI-integrated websites has created a growing demand for more sophisticated tools to protect devices and networks, especially in light of the emergence of AI-generated malware. Indeed, numerous studies anticipated the threats posed by this type of malware and proposed a variety of solutions to address this issue. In this context, most research introducing generative AI frameworks deals with image-based data, prompting the need to analyze tabular network data. We propose AAE-DRL, an Intrusion Detection System (IDS) that utilizes generative AI and deep reinforcement learning to replicate and predict intrusion behavior. We demonstrate the advantages and limitations of combining reconstruction and adversarial learning objectives with Deep Reinforcement Learning (DRL) in terms of intrusion detection, data generation, and minority sampling. Our approach achieved 89% accuracy, 90% precision, 91% recall, 90% F1-score on the augmented dataset with a 97% Area Under the Curve (AUC).

Paper Citation

in Harvard Style

Ben Makhlouf I., Kilani G., Jaafar F. and Nakouri H. (2025). A Hybrid Approach to Improve the Intrusion Detection Systems Using Generative Artificial Intelligence and Deep Reinforcement Learning. In Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT; ISBN 978-989-758-760-3, SciTePress, pages 467-474. DOI: 10.5220/0013567700003979

in Bibtex Style

@conference{secrypt25,
author={Ines Ben Makhlouf and Ghassen Kilani and Fehmi Jaafar and Haïfa Nakouri},
title={A Hybrid Approach to Improve the Intrusion Detection Systems Using Generative Artificial Intelligence and Deep Reinforcement Learning},
booktitle={Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT},
year={2025},
pages={467-474},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013567700003979},
isbn={978-989-758-760-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT
TI - A Hybrid Approach to Improve the Intrusion Detection Systems Using Generative Artificial Intelligence and Deep Reinforcement Learning
SN - 978-989-758-760-3
AU - Ben Makhlouf I.
AU - Kilani G.
AU - Jaafar F.
AU - Nakouri H.
PY - 2025
SP - 467
EP - 474
DO - 10.5220/0013567700003979
PB - SciTePress