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 Proceedings Article
In: K., Adi; O., Nguena Timo; N., Boulahia-Cuppens; D., Espes; N., Stakhanova; M., Omar (Ed.): Lect. Notes Comput. Sci., pp. 85–99, Springer Science and Business Media Deutschland GmbH, 2026, ISBN: 03029743 (ISSN); 978-303220731-9 (ISBN), (Journal Abbreviation: Lect. Notes Comput. Sci.).
Abstract | Links | BibTeX | Tags: 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.
Zetout, A.; Allili, M. S.
CSDNet: Context-Aware Segmentation of Disaster Aerial Imagery Using Detection-Guided Features and Lightweight Transformers Journal Article
In: Remote Sensing, vol. 17, no. 14, 2025, ISSN: 20724292 (ISSN).
Abstract | Links | BibTeX | Tags: Aerial imagery, Affected area, Antennas, Class imbalance, Context-Aware, Contextual semantic segmentation, Contextual semantics, Detection, disaster response, Disaster-response, Emergency services, Error detection, Feature extraction, Lightweight model, Semantic segmentation, Semantics
@article{zetout_csdnet_2025,
title = {CSDNet: Context-Aware Segmentation of Disaster Aerial Imagery Using Detection-Guided Features and Lightweight Transformers},
author = {A. Zetout and M. S. Allili},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105011677142&doi=10.3390%2Frs17142337&partnerID=40&md5=a83db334b208d065476e0026ad0ee416},
doi = {10.3390/rs17142337},
issn = {20724292 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Remote Sensing},
volume = {17},
number = {14},
abstract = {Accurate multi-class semantic segmentation of disaster-affected areas is essential for rapid response and effective recovery planning. We present CSDNet, a context-aware segmentation model tailored to disaster scene scenarios, designed to improve segmentation of both large-scale disaster zones and small, underrepresented classes. The architecture combines a lightweight transformer module for global context modeling with depthwise separable convolutions (DWSCs) to enhance efficiency without compromising representational capacity. Additionally, we introduce a detection-guided feature fusion mechanism that integrates outputs from auxiliary detection tasks to mitigate class imbalance and improve discrimination of visually similar categories. Extensive experiments on several public datasets demonstrate that our model significantly improves segmentation of both man-made infrastructure and natural damage-related features, offering a robust and efficient solution for post-disaster analysis. © 2025 by the authors.},
keywords = {Aerial imagery, Affected area, Antennas, Class imbalance, Context-Aware, Contextual semantic segmentation, Contextual semantics, Detection, disaster response, Disaster-response, Emergency services, Error detection, Feature extraction, Lightweight model, Semantic segmentation, Semantics},
pubstate = {published},
tppubtype = {article}
}
Accurate multi-class semantic segmentation of disaster-affected areas is essential for rapid response and effective recovery planning. We present CSDNet, a context-aware segmentation model tailored to disaster scene scenarios, designed to improve segmentation of both large-scale disaster zones and small, underrepresented classes. The architecture combines a lightweight transformer module for global context modeling with depthwise separable convolutions (DWSCs) to enhance efficiency without compromising representational capacity. Additionally, we introduce a detection-guided feature fusion mechanism that integrates outputs from auxiliary detection tasks to mitigate class imbalance and improve discrimination of visually similar categories. Extensive experiments on several public datasets demonstrate that our model significantly improves segmentation of both man-made infrastructure and natural damage-related features, offering a robust and efficient solution for post-disaster analysis. © 2025 by the authors.
3.
Zetout, A.; Allili, M. S.
CSDNet: Context-Aware Segmentation of Disaster Aerial Imagery Using Detection-Guided Features and Lightweight Transformers Journal Article
In: Remote Sensing, vol. 17, no. 14, 2025, ISSN: 20724292 (ISSN).
Abstract | Links | BibTeX | Tags: Aerial imagery, Affected area, Antennas, Class imbalance, Context-Aware, Contextual semantic segmentation, Contextual semantics, Detection, disaster response, Disaster-response, Emergency services, Error detection, Feature extraction, Lightweight model, Semantic segmentation, Semantics
@article{zetoutCSDNetContextAwareSegmentation2025,
title = {CSDNet: Context-Aware Segmentation of Disaster Aerial Imagery Using Detection-Guided Features and Lightweight Transformers},
author = {A. Zetout and M. S. Allili},
url = {https://www.scopus.com/pages/publications/105011677142?origin=resultslist},
doi = {10.3390/rs17142337},
issn = {20724292 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Remote Sensing},
volume = {17},
number = {14},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
abstract = {Accurate multi-class semantic segmentation of disaster-affected areas is essential for rapid response and effective recovery planning. We present CSDNet, a context-aware segmentation model tailored to disaster scene scenarios, designed to improve segmentation of both large-scale disaster zones and small, underrepresented classes. The architecture combines a lightweight transformer module for global context modeling with depthwise separable convolutions (DWSCs) to enhance efficiency without compromising representational capacity. Additionally, we introduce a detection-guided feature fusion mechanism that integrates outputs from auxiliary detection tasks to mitigate class imbalance and improve discrimination of visually similar categories. Extensive experiments on several public datasets demonstrate that our model significantly improves segmentation of both man-made infrastructure and natural damage-related features, offering a robust and efficient solution for post-disaster analysis. © 2025 by the authors.},
keywords = {Aerial imagery, Affected area, Antennas, Class imbalance, Context-Aware, Contextual semantic segmentation, Contextual semantics, Detection, disaster response, Disaster-response, Emergency services, Error detection, Feature extraction, Lightweight model, Semantic segmentation, Semantics},
pubstate = {published},
tppubtype = {article}
}
Accurate multi-class semantic segmentation of disaster-affected areas is essential for rapid response and effective recovery planning. We present CSDNet, a context-aware segmentation model tailored to disaster scene scenarios, designed to improve segmentation of both large-scale disaster zones and small, underrepresented classes. The architecture combines a lightweight transformer module for global context modeling with depthwise separable convolutions (DWSCs) to enhance efficiency without compromising representational capacity. Additionally, we introduce a detection-guided feature fusion mechanism that integrates outputs from auxiliary detection tasks to mitigate class imbalance and improve discrimination of visually similar categories. Extensive experiments on several public datasets demonstrate that our model significantly improves segmentation of both man-made infrastructure and natural damage-related features, offering a robust and efficient solution for post-disaster analysis. © 2025 by the authors.
4.
Zetout, A.; Allili, M. S.
CSDNet: Context-Aware Segmentation of Disaster Aerial Imagery Using Detection-Guided Features and Lightweight Transformers Journal Article
In: Remote Sensing, vol. 17, no. 14, 2025, ISSN: 20724292 (ISSN).
Abstract | Links | BibTeX | Tags: Aerial imagery, Affected area, Antennas, Class imbalance, Context-Aware, Contextual semantic segmentation, Contextual semantics, Detection, disaster response, Disaster-response, Emergency services, Error detection, Feature extraction, Lightweight model, Semantic segmentation, Semantics
@article{zetoutCSDNetContextAwareSegmentation2025a,
title = {CSDNet: Context-Aware Segmentation of Disaster Aerial Imagery Using Detection-Guided Features and Lightweight Transformers},
author = {A. Zetout and M. S. Allili},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105011677142&doi=10.3390%2Frs17142337&partnerID=40&md5=a83db334b208d065476e0026ad0ee416},
doi = {10.3390/rs17142337},
issn = {20724292 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Remote Sensing},
volume = {17},
number = {14},
abstract = {Accurate multi-class semantic segmentation of disaster-affected areas is essential for rapid response and effective recovery planning. We present CSDNet, a context-aware segmentation model tailored to disaster scene scenarios, designed to improve segmentation of both large-scale disaster zones and small, underrepresented classes. The architecture combines a lightweight transformer module for global context modeling with depthwise separable convolutions (DWSCs) to enhance efficiency without compromising representational capacity. Additionally, we introduce a detection-guided feature fusion mechanism that integrates outputs from auxiliary detection tasks to mitigate class imbalance and improve discrimination of visually similar categories. Extensive experiments on several public datasets demonstrate that our model significantly improves segmentation of both man-made infrastructure and natural damage-related features, offering a robust and efficient solution for post-disaster analysis. © 2025 by the authors.},
keywords = {Aerial imagery, Affected area, Antennas, Class imbalance, Context-Aware, Contextual semantic segmentation, Contextual semantics, Detection, disaster response, Disaster-response, Emergency services, Error detection, Feature extraction, Lightweight model, Semantic segmentation, Semantics},
pubstate = {published},
tppubtype = {article}
}
Accurate multi-class semantic segmentation of disaster-affected areas is essential for rapid response and effective recovery planning. We present CSDNet, a context-aware segmentation model tailored to disaster scene scenarios, designed to improve segmentation of both large-scale disaster zones and small, underrepresented classes. The architecture combines a lightweight transformer module for global context modeling with depthwise separable convolutions (DWSCs) to enhance efficiency without compromising representational capacity. Additionally, we introduce a detection-guided feature fusion mechanism that integrates outputs from auxiliary detection tasks to mitigate class imbalance and improve discrimination of visually similar categories. Extensive experiments on several public datasets demonstrate that our model significantly improves segmentation of both man-made infrastructure and natural damage-related features, offering a robust and efficient solution for post-disaster analysis. © 2025 by the authors.