Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Guerziz, I.; Falk, T.; Le, L. B.; Houda, Z. A. E.
Domain Adversarial Neural Networks with Adversarial Robustness Evaluation for Intrusion Detection Systems Proceedings Article
In: K., Adi; O., Nguena Timo; N., Boulahia-Cuppens; D., Espes; N., Stakhanova; M., Omar (Ed.): Lect. Notes Comput. Sci., pp. 153–165, 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 Attacks, Adversarial neural network, Adversarial Neural Networks, Attack Resilience, Attack resiliences, Computer crime, Domain adaptation, Fast gradient sign method, FGSM, Gradient-descent, Intrusion Detection, Intrusion Detection Systems, Network intrusion, Network intrusion detection systems, Network security, Neural networks, Neural-networks, PGD, Projected gradient, Projected gradient descent
@inproceedings{guerzizDomainAdversarialNeural2026,
title = {Domain Adversarial Neural Networks with Adversarial Robustness Evaluation for Intrusion Detection Systems},
author = {I. Guerziz and T. Falk and L. B. Le and Z. A. E. Houda},
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/105046102448?origin=resultslist},
doi = {10.1007/978-3-032-20732-6_10},
isbn = {03029743 (ISSN); 978-303220731-9 (ISBN)},
year = {2026},
date = {2026-01-01},
booktitle = {Lect. Notes Comput. Sci.},
volume = {16295 LNCS},
pages = {153–165},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {Modern Network Intrusion Detection Systems (NIDS) face the dual challenge of maintaining performance across diverse network environments while resisting adversarial manipulations. This paper investigates the intersection of domain adaptation and adversarial robustness in NIDS, a topic that has not been extensively studied. We implement a Domain-Adversarial Neural Network (DANN) with dynamic gradient reversal to adapt models from NSL-KDD to UNSW-NB15. To evaluate security, we assess the model under Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks. Additionally, we introduce FGSM-based adversarial training to enhance robustness. Our results show that while domain adaptation improves cross-domain detection, it also increases susceptibility to adversarial attacks. Incorporating adversarial training mitigates this vulnerability, improving resilience without compromising performance on clean data. These findings provide key insights for designing adaptive and secure intrusion detection systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.},
note = {Journal Abbreviation: Lect. Notes Comput. Sci.},
keywords = {Adversarial Attacks, Adversarial neural network, Adversarial Neural Networks, Attack Resilience, Attack resiliences, Computer crime, Domain adaptation, Fast gradient sign method, FGSM, Gradient-descent, Intrusion Detection, Intrusion Detection Systems, Network intrusion, Network intrusion detection systems, Network security, Neural networks, Neural-networks, PGD, Projected gradient, Projected gradient descent},
pubstate = {published},
tppubtype = {inproceedings}
}
Modern Network Intrusion Detection Systems (NIDS) face the dual challenge of maintaining performance across diverse network environments while resisting adversarial manipulations. This paper investigates the intersection of domain adaptation and adversarial robustness in NIDS, a topic that has not been extensively studied. We implement a Domain-Adversarial Neural Network (DANN) with dynamic gradient reversal to adapt models from NSL-KDD to UNSW-NB15. To evaluate security, we assess the model under Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks. Additionally, we introduce FGSM-based adversarial training to enhance robustness. Our results show that while domain adaptation improves cross-domain detection, it also increases susceptibility to adversarial attacks. Incorporating adversarial training mitigates this vulnerability, improving resilience without compromising performance on clean data. These findings provide key insights for designing adaptive and secure intrusion detection systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
2.
Allaoui, M.; Hedjam, R.; Bouanane, K.; Allili, M. S.; Kherfi, M. L.; Belhaouari, S. B.
Exploring non-negativity for improved manifold embedding: Application to t-SNE Journal Article
In: Knowledge-Based Systems, vol. 330, 2025, ISSN: 09507051 (ISSN).
Abstract | Links | BibTeX | Tags: Dimensionality reduction, Embedding technique, Embeddings, Gradient methods, Gradient-descent, Manifold embedding, Matrix algebra, Non-negative matrix factorization, Non-negativity, Nonnegative matrix factorization, Nonnegativity constraints, Performance, T-SNE
@article{allaoui_exploring_2025,
title = {Exploring non-negativity for improved manifold embedding: Application to t-SNE},
author = {M. Allaoui and R. Hedjam and K. Bouanane and M. S. Allili and M. L. Kherfi and S. B. Belhaouari},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105018098090&doi=10.1016%2Fj.knosys.2025.114547&partnerID=40&md5=237540c38a928146d589b96cd6888547},
doi = {10.1016/j.knosys.2025.114547},
issn = {09507051 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Knowledge-Based Systems},
volume = {330},
abstract = {Drawing inspiration from Non-negative Matrix Factorization (NMF), this paper explores the potential of incorporating non-negativity constraints into embedding techniques, with a focus on t-SNE as an application. Specifically, we investigate the following questions: Can enforcing non-negativity in the embedding space enhance interpretability and improve the quality of embedded data? By prioritizing non-negativity, can embedding methods achieve better performance and more meaningful representations? Additionally, does enforcing non-negativity in the embedded space help preserve both the local and global structure of data in the manifold, leading to more accurate and interpretable embeddings? In this work, we could show both objectively and subjectively how enforcing t-SNE to leverage the non-negativity of the data addresses the raised questions. To achieve this, we introduced a novel approach to transforming the additive update rule of the gradient descent used by t-SNE to a multiplicative counterpart to enforce the non-negativity in the embedded space. However, grappling with full non-negativity in the gradient descent formula presents challenges, prompting our focus solely on the (yi−yj) term, resulting in a semi-non-negative t-SNE algorithm, shortly named SN-tSNE. Nevertheless, experimental findings substantiate the significant impact of the proposed update rule on the performance and efficacy of the SN-tSNE algorithm. Furthermore, additional experiments are performed to compare SN-tSNE with its precursor t-SNE, as well as the competitive embedding technique UMAP, alongside other relevant embedding and dimensionality reduction models like NMF. The source code of SN-tSNE is available on GitHub (https://github.com/M-Allaoui/SN-tSNE.git). © 2025},
keywords = {Dimensionality reduction, Embedding technique, Embeddings, Gradient methods, Gradient-descent, Manifold embedding, Matrix algebra, Non-negative matrix factorization, Non-negativity, Nonnegative matrix factorization, Nonnegativity constraints, Performance, T-SNE},
pubstate = {published},
tppubtype = {article}
}
Drawing inspiration from Non-negative Matrix Factorization (NMF), this paper explores the potential of incorporating non-negativity constraints into embedding techniques, with a focus on t-SNE as an application. Specifically, we investigate the following questions: Can enforcing non-negativity in the embedding space enhance interpretability and improve the quality of embedded data? By prioritizing non-negativity, can embedding methods achieve better performance and more meaningful representations? Additionally, does enforcing non-negativity in the embedded space help preserve both the local and global structure of data in the manifold, leading to more accurate and interpretable embeddings? In this work, we could show both objectively and subjectively how enforcing t-SNE to leverage the non-negativity of the data addresses the raised questions. To achieve this, we introduced a novel approach to transforming the additive update rule of the gradient descent used by t-SNE to a multiplicative counterpart to enforce the non-negativity in the embedded space. However, grappling with full non-negativity in the gradient descent formula presents challenges, prompting our focus solely on the (yi−yj) term, resulting in a semi-non-negative t-SNE algorithm, shortly named SN-tSNE. Nevertheless, experimental findings substantiate the significant impact of the proposed update rule on the performance and efficacy of the SN-tSNE algorithm. Furthermore, additional experiments are performed to compare SN-tSNE with its precursor t-SNE, as well as the competitive embedding technique UMAP, alongside other relevant embedding and dimensionality reduction models like NMF. The source code of SN-tSNE is available on GitHub (https://github.com/M-Allaoui/SN-tSNE.git). © 2025
3.
Allaoui, M.; Hedjam, R.; Bouanane, K.; Allili, M. S.; Kherfi, M. L.; Belhaouari, S. B.
Exploring non-negativity for improved manifold embedding: Application to t-SNE Journal Article
In: Knowledge-Based Systems, vol. 330, 2025, ISSN: 09507051 (ISSN).
Abstract | Links | BibTeX | Tags: Dimensionality reduction, Embedding technique, Embeddings, Gradient methods, Gradient-descent, Manifold embedding, Matrix algebra, Non-negative matrix factorization, Non-negativity, Nonnegative matrix factorization, Nonnegativity constraints, Performance, T-SNE
@article{allaouiExploringNonnegativityImproved2025,
title = {Exploring non-negativity for improved manifold embedding: Application to t-SNE},
author = {M. Allaoui and R. Hedjam and K. Bouanane and M. S. Allili and M. L. Kherfi and S. B. Belhaouari},
url = {https://www.scopus.com/pages/publications/105018098090?origin=resultslist},
doi = {10.1016/j.knosys.2025.114547},
issn = {09507051 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Knowledge-Based Systems},
volume = {330},
publisher = {Elsevier B.V.},
abstract = {Drawing inspiration from Non-negative Matrix Factorization (NMF), this paper explores the potential of incorporating non-negativity constraints into embedding techniques, with a focus on t-SNE as an application. Specifically, we investigate the following questions: Can enforcing non-negativity in the embedding space enhance interpretability and improve the quality of embedded data? By prioritizing non-negativity, can embedding methods achieve better performance and more meaningful representations? Additionally, does enforcing non-negativity in the embedded space help preserve both the local and global structure of data in the manifold, leading to more accurate and interpretable embeddings? In this work, we could show both objectively and subjectively how enforcing t-SNE to leverage the non-negativity of the data addresses the raised questions. To achieve this, we introduced a novel approach to transforming the additive update rule of the gradient descent used by t-SNE to a multiplicative counterpart to enforce the non-negativity in the embedded space. However, grappling with full non-negativity in the gradient descent formula presents challenges, prompting our focus solely on the (yi−yj) term, resulting in a semi-non-negative t-SNE algorithm, shortly named SN-tSNE. Nevertheless, experimental findings substantiate the significant impact of the proposed update rule on the performance and efficacy of the SN-tSNE algorithm. Furthermore, additional experiments are performed to compare SN-tSNE with its precursor t-SNE, as well as the competitive embedding technique UMAP, alongside other relevant embedding and dimensionality reduction models like NMF. The source code of SN-tSNE is available on GitHub (https://github.com/M-Allaoui/SN-tSNE.git). © 2025},
keywords = {Dimensionality reduction, Embedding technique, Embeddings, Gradient methods, Gradient-descent, Manifold embedding, Matrix algebra, Non-negative matrix factorization, Non-negativity, Nonnegative matrix factorization, Nonnegativity constraints, Performance, T-SNE},
pubstate = {published},
tppubtype = {article}
}
Drawing inspiration from Non-negative Matrix Factorization (NMF), this paper explores the potential of incorporating non-negativity constraints into embedding techniques, with a focus on t-SNE as an application. Specifically, we investigate the following questions: Can enforcing non-negativity in the embedding space enhance interpretability and improve the quality of embedded data? By prioritizing non-negativity, can embedding methods achieve better performance and more meaningful representations? Additionally, does enforcing non-negativity in the embedded space help preserve both the local and global structure of data in the manifold, leading to more accurate and interpretable embeddings? In this work, we could show both objectively and subjectively how enforcing t-SNE to leverage the non-negativity of the data addresses the raised questions. To achieve this, we introduced a novel approach to transforming the additive update rule of the gradient descent used by t-SNE to a multiplicative counterpart to enforce the non-negativity in the embedded space. However, grappling with full non-negativity in the gradient descent formula presents challenges, prompting our focus solely on the (yi−yj) term, resulting in a semi-non-negative t-SNE algorithm, shortly named SN-tSNE. Nevertheless, experimental findings substantiate the significant impact of the proposed update rule on the performance and efficacy of the SN-tSNE algorithm. Furthermore, additional experiments are performed to compare SN-tSNE with its precursor t-SNE, as well as the competitive embedding technique UMAP, alongside other relevant embedding and dimensionality reduction models like NMF. The source code of SN-tSNE is available on GitHub (https://github.com/M-Allaoui/SN-tSNE.git). © 2025
4.
Allaoui, M.; Hedjam, R.; Bouanane, K.; Allili, M. S.; Kherfi, M. L.; Belhaouari, S. B.
Exploring non-negativity for improved manifold embedding: Application to t-SNE Journal Article
In: Knowledge-Based Systems, vol. 330, 2025, ISSN: 09507051 (ISSN).
Abstract | Links | BibTeX | Tags: Dimensionality reduction, Embedding technique, Embeddings, Gradient methods, Gradient-descent, Manifold embedding, Matrix algebra, Non-negative matrix factorization, Non-negativity, Nonnegative matrix factorization, Nonnegativity constraints, Performance, T-SNE
@article{allaouiExploringNonnegativityImproved2025a,
title = {Exploring non-negativity for improved manifold embedding: Application to t-SNE},
author = {M. Allaoui and R. Hedjam and K. Bouanane and M. S. Allili and M. L. Kherfi and S. B. Belhaouari},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105018098090&doi=10.1016%2Fj.knosys.2025.114547&partnerID=40&md5=237540c38a928146d589b96cd6888547},
doi = {10.1016/j.knosys.2025.114547},
issn = {09507051 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Knowledge-Based Systems},
volume = {330},
abstract = {Drawing inspiration from Non-negative Matrix Factorization (NMF), this paper explores the potential of incorporating non-negativity constraints into embedding techniques, with a focus on t-SNE as an application. Specifically, we investigate the following questions: Can enforcing non-negativity in the embedding space enhance interpretability and improve the quality of embedded data? By prioritizing non-negativity, can embedding methods achieve better performance and more meaningful representations? Additionally, does enforcing non-negativity in the embedded space help preserve both the local and global structure of data in the manifold, leading to more accurate and interpretable embeddings? In this work, we could show both objectively and subjectively how enforcing t-SNE to leverage the non-negativity of the data addresses the raised questions. To achieve this, we introduced a novel approach to transforming the additive update rule of the gradient descent used by t-SNE to a multiplicative counterpart to enforce the non-negativity in the embedded space. However, grappling with full non-negativity in the gradient descent formula presents challenges, prompting our focus solely on the (yi−yj) term, resulting in a semi-non-negative t-SNE algorithm, shortly named SN-tSNE. Nevertheless, experimental findings substantiate the significant impact of the proposed update rule on the performance and efficacy of the SN-tSNE algorithm. Furthermore, additional experiments are performed to compare SN-tSNE with its precursor t-SNE, as well as the competitive embedding technique UMAP, alongside other relevant embedding and dimensionality reduction models like NMF. The source code of SN-tSNE is available on GitHub (https://github.com/M-Allaoui/SN-tSNE.git). © 2025},
keywords = {Dimensionality reduction, Embedding technique, Embeddings, Gradient methods, Gradient-descent, Manifold embedding, Matrix algebra, Non-negative matrix factorization, Non-negativity, Nonnegative matrix factorization, Nonnegativity constraints, Performance, T-SNE},
pubstate = {published},
tppubtype = {article}
}
Drawing inspiration from Non-negative Matrix Factorization (NMF), this paper explores the potential of incorporating non-negativity constraints into embedding techniques, with a focus on t-SNE as an application. Specifically, we investigate the following questions: Can enforcing non-negativity in the embedding space enhance interpretability and improve the quality of embedded data? By prioritizing non-negativity, can embedding methods achieve better performance and more meaningful representations? Additionally, does enforcing non-negativity in the embedded space help preserve both the local and global structure of data in the manifold, leading to more accurate and interpretable embeddings? In this work, we could show both objectively and subjectively how enforcing t-SNE to leverage the non-negativity of the data addresses the raised questions. To achieve this, we introduced a novel approach to transforming the additive update rule of the gradient descent used by t-SNE to a multiplicative counterpart to enforce the non-negativity in the embedded space. However, grappling with full non-negativity in the gradient descent formula presents challenges, prompting our focus solely on the (yi−yj) term, resulting in a semi-non-negative t-SNE algorithm, shortly named SN-tSNE. Nevertheless, experimental findings substantiate the significant impact of the proposed update rule on the performance and efficacy of the SN-tSNE algorithm. Furthermore, additional experiments are performed to compare SN-tSNE with its precursor t-SNE, as well as the competitive embedding technique UMAP, alongside other relevant embedding and dimensionality reduction models like NMF. The source code of SN-tSNE is available on GitHub (https://github.com/M-Allaoui/SN-tSNE.git). © 2025