Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Zoungrana, A. F.; Moudoud, H.; Tajeuna, E. G.; Adi, K.
Adversarial Ensemble Framework: Leveraging GANs for Robust Intrusion Detection in IoT Networks Article d'actes
Dans: K., Adi; O., Nguena Timo; N., Boulahia-Cuppens; D., Espes; N., Stakhanova; M., Omar (Ed.): Lect. Notes Comput. Sci., p. 85–99, Springer Science and Business Media Deutschland GmbH, 2026, ISBN: 03029743 (ISSN); 978-303220731-9 (ISBN), (Journal Abbreviation: Lect. Notes Comput. Sci.).
Résumé | Liens | BibTeX | Étiquettes: Adversarial networks, Class imbalance, Computer crime, Concept drifts, Gallium nitride, Generative adversarial networks, Internet of thing network, Internet of things, Intrusion Detection, Intrusion Detection Systems, Intrusion-Detection, IoT Networks, Key Issues, Network intrusion, Network security, Rapid expansion, Security, Security challenges
@inproceedings{zoungranaAdversarialEnsembleFramework2026,
title = {Adversarial Ensemble Framework: Leveraging GANs for Robust Intrusion Detection in IoT Networks},
author = {A. F. Zoungrana and H. Moudoud and E. G. Tajeuna and K. Adi},
editor = {Adi K. and Nguena Timo O. and Boulahia-Cuppens N. and Espes D. and Stakhanova N. and Omar M.},
url = {https://www.scopus.com/pages/publications/105046136116?origin=resultslist},
doi = {10.1007/978-3-032-20732-6_6},
isbn = {03029743 (ISSN); 978-303220731-9 (ISBN)},
year = {2026},
date = {2026-01-01},
booktitle = {Lect. Notes Comput. Sci.},
volume = {16295 LNCS},
pages = {85–99},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {The rapid expansion of Internet of Things (IoT) devices introduces complex security challenges that traditional intrusion detection systems struggle to address. This paper proposes an Adversarial Ensemble Framework using Generative Adversarial Networks (GANs) to improve the accuracy and resilience of intrusion detection in IoT environments. The framework tackles key issues such as class imbalance, concept drift, and adversarial attacks by employing multiple GAN variants such as Vanilla GAN, Conditional GAN (CGAN), and Wasserstein GAN (WGAN) to generate high-quality synthetic attack data. A dynamic ensemble learning mechanism selects the most effective model for each attack type based on performance metrics. Experiments on NSL-KDD and CIC-IDS2017 show that WGAN yields the most effective synthetic data, contributing to a detection rate of up to 96%. The approach proves particularly effective in identifying rare attacks, making it a scalable and adaptive solution for IoT security. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.},
note = {Journal Abbreviation: Lect. Notes Comput. Sci.},
keywords = {Adversarial networks, Class imbalance, Computer crime, Concept drifts, Gallium nitride, Generative adversarial networks, Internet of thing network, Internet of things, Intrusion Detection, Intrusion Detection Systems, Intrusion-Detection, IoT Networks, Key Issues, Network intrusion, Network security, Rapid expansion, Security, Security challenges},
pubstate = {published},
tppubtype = {inproceedings}
}
The rapid expansion of Internet of Things (IoT) devices introduces complex security challenges that traditional intrusion detection systems struggle to address. This paper proposes an Adversarial Ensemble Framework using Generative Adversarial Networks (GANs) to improve the accuracy and resilience of intrusion detection in IoT environments. The framework tackles key issues such as class imbalance, concept drift, and adversarial attacks by employing multiple GAN variants such as Vanilla GAN, Conditional GAN (CGAN), and Wasserstein GAN (WGAN) to generate high-quality synthetic attack data. A dynamic ensemble learning mechanism selects the most effective model for each attack type based on performance metrics. Experiments on NSL-KDD and CIC-IDS2017 show that WGAN yields the most effective synthetic data, contributing to a detection rate of up to 96%. The approach proves particularly effective in identifying rare attacks, making it a scalable and adaptive solution for IoT security. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
2.
Moudoud, H.; Houda, Z. A. E.; Brik, B.
LLMs to Secure Consumer Networks: Open Problems and Future Directions Article de journal
Dans: IEEE Consumer Electronics Magazine, vol. 14, no 5, p. 51–59, 2025, ISSN: 21622248 (ISSN).
Résumé | Liens | BibTeX | Étiquettes: 'current, Comprehensive research, Cyber threats, Defence mechanisms, Forward looking, Generative adversarial networks, Innovative solutions, Language model, Research problems, Security mechanism, Smart Home Technology
@article{moudoudLLMsSecureConsumer2025,
title = {LLMs to Secure Consumer Networks: Open Problems and Future Directions},
author = {H. Moudoud and Z. A. E. Houda and B. Brik},
url = {https://www.scopus.com/pages/publications/85217963109?origin=resultslist},
doi = {10.1109/MCE.2025.3542247},
issn = {21622248 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {IEEE Consumer Electronics Magazine},
volume = {14},
number = {5},
pages = {51–59},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The increasing complexity of consumer networks, characterized by the rapid adoption of Internet of Things devices and smart home technologies, exposes significant limitations in traditional security mechanisms. These challenges drive a growing interest in innovative solutions, such as generative artificial intelligence, including large language models (LLMs) to ensure the security of consumer networks from evolving cyber threats. In this article, we present a forward-looking perspective on the role of LLMs in securing consumer networks. Then, we present a comprehensive study of attacks targeting LLMs and current defense mechanisms/strategies. Finally, we present a set of core research problems and a comprehensive research agenda that identifies future directions to advance LLM capabilities for consumer network security. © 2012 IEEE.},
keywords = {'current, Comprehensive research, Cyber threats, Defence mechanisms, Forward looking, Generative adversarial networks, Innovative solutions, Language model, Research problems, Security mechanism, Smart Home Technology},
pubstate = {published},
tppubtype = {article}
}
The increasing complexity of consumer networks, characterized by the rapid adoption of Internet of Things devices and smart home technologies, exposes significant limitations in traditional security mechanisms. These challenges drive a growing interest in innovative solutions, such as generative artificial intelligence, including large language models (LLMs) to ensure the security of consumer networks from evolving cyber threats. In this article, we present a forward-looking perspective on the role of LLMs in securing consumer networks. Then, we present a comprehensive study of attacks targeting LLMs and current defense mechanisms/strategies. Finally, we present a set of core research problems and a comprehensive research agenda that identifies future directions to advance LLM capabilities for consumer network security. © 2012 IEEE.
3.
Soltani, N.; Nejadshamsi, S.; Houda, Z. A. El; Khoury, R.; Costa, K. A. P.; Falk, T. H.; Avila, A. R.
Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks Article d'actes
Dans: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern., p. 39–44, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 1062922X (ISSN); 979-833153358-8 (ISBN), (Journal Abbreviation: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.).
Résumé | Liens | BibTeX | Étiquettes: Adversarial machine learning, Adversarial networks, Classification (of information), Computer crime, Fast gradient sign method, Fast Gradient Sign Method (FGSM), Generative adversarial network, Generative Adversarial Network (GAN), Generative adversarial networks, Generative model, Generative Models, Intrusion Detection, Intrusion-Detection, Learning algorithms, Learning systems, Machine-learning, Multi-layers, Network intrusion, Network intrusion detection systems, Network layers, Network security, Second layer, Stackings
@inproceedings{soltaniEnhancingNetworkIntrusion2025,
title = {Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks},
author = {N. Soltani and S. Nejadshamsi and Z. A. El Houda and R. Khoury and K. A. P. Costa and T. H. Falk and A. R. Avila},
url = {https://www.scopus.com/pages/publications/105033159769?origin=resultslist},
doi = {10.1109/SMC58881.2025.11342479},
isbn = {1062922X (ISSN); 979-833153358-8 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
pages = {39–44},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems (NIDS), they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS towards adversarial attacks. To that end, we explore two adversarial methods for generating malicious network traffic. The first method is based on Generative Adversarial Networks (GAN) and the second one is the Fast Gradient Sign Method (FGSM). The adversarial examples generated by these methods are then used to evaluate a novel multilayer defense mechanism, specifically designed to mitigate the vulnerability of ML-based NIDS. Our solution consists of one layer of stacking classifiers and a second layer based on an autoencoder. If the incoming network data are classified as benign by the first layer, the second layer is activated to ensure that the decision made by the stacking classifier is correct. We also incorporated adversarial training to further improve the robustness of our solution. Experiments on two datasets, namely UNSW-NB15 and NSL-KDD, demonstrate that the proposed approach increases resilience to adversarial attacks. © 2025 IEEE.},
note = {Journal Abbreviation: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
keywords = {Adversarial machine learning, Adversarial networks, Classification (of information), Computer crime, Fast gradient sign method, Fast Gradient Sign Method (FGSM), Generative adversarial network, Generative Adversarial Network (GAN), Generative adversarial networks, Generative model, Generative Models, Intrusion Detection, Intrusion-Detection, Learning algorithms, Learning systems, Machine-learning, Multi-layers, Network intrusion, Network intrusion detection systems, Network layers, Network security, Second layer, Stackings},
pubstate = {published},
tppubtype = {inproceedings}
}
Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems (NIDS), they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS towards adversarial attacks. To that end, we explore two adversarial methods for generating malicious network traffic. The first method is based on Generative Adversarial Networks (GAN) and the second one is the Fast Gradient Sign Method (FGSM). The adversarial examples generated by these methods are then used to evaluate a novel multilayer defense mechanism, specifically designed to mitigate the vulnerability of ML-based NIDS. Our solution consists of one layer of stacking classifiers and a second layer based on an autoencoder. If the incoming network data are classified as benign by the first layer, the second layer is activated to ensure that the decision made by the stacking classifier is correct. We also incorporated adversarial training to further improve the robustness of our solution. Experiments on two datasets, namely UNSW-NB15 and NSL-KDD, demonstrate that the proposed approach increases resilience to adversarial attacks. © 2025 IEEE.