Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Malasi, J. -J. M.; Moudoud, H.; Missaoui, R.
CausalGraph: When Causal Reasoning Meets Large Language Models for Intrusion Detection Systems Article d'actes
Dans: Dig Tech Pap IEEE Int Conf Consum Electron, Institute of Electrical and Electronics Engineers Inc., 2026, ISBN: 0747668X (ISSN); 979-833155343-2 (ISBN), (Journal Abbreviation: Dig Tech Pap IEEE Int Conf Consum Electron).
Résumé | Liens | BibTeX | Étiquettes: Alarm systems, Budget control, causal reasoning, Chains, Computer crime, Concept Drift, Concept drifts, Conformal Risk Control, Counterfactuals, Generative AI, Human computer interaction, Intrusion Detection, Intrusion Detection Systems, Intrusion-Detection, Knowledge based systems, Language model, LLM, LLMs, Network intrusion, Network security, Risks controls, Sampling
@inproceedings{malasiCausalGraphWhenCausal2026,
title = {CausalGraph: When Causal Reasoning Meets Large Language Models for Intrusion Detection Systems},
author = {J. -J. M. Malasi and H. Moudoud and R. Missaoui},
url = {https://www.scopus.com/pages/publications/105037367854?origin=resultslist},
doi = {10.1109/ICCE67443.2026.11449614},
isbn = {0747668X (ISSN); 979-833155343-2 (ISBN)},
year = {2026},
date = {2026-01-01},
booktitle = {Dig Tech Pap IEEE Int Conf Consum Electron},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Modern intrusion detection systems often achieve impressive benchmark accuracy yet fail in real-world deployment, where network behavior and attacker tactics continuously evolve. Under concept drift, decision boundaries learned offline can diverge from operational reality, triggering false-alarm cascades and creating detection blind spots that erode analyst trust. In this paper, we propose CausalGraph-IDS, a causal and language-model-assisted intrusion detection framework that moves beyond purely correlational scoring by explicitly verifying multi-stage attack chains. Additionally, we propose CHAIN-CRC, a unified algorithm that (i) learns a constrained attack-chain causal graph guided by knowledge-based priors derived from widely used adversary behavior taxonomies, (ii) computes robustness scores by testing whether alarms persist under feasible counterfactual security interventions, and (iii) applies conformal risk control to enforce operator-defined false-positive budgets with finite-sample guarantees.Generative models are integrated in strictly assistive roles through three modules: prior induction to distill causal constraints from unstructured threat reports, counterfactual generation to propose realistic and operationally feasible interventions, and causal logic justification to produce human-readable explanations grounded in the learned attack chain. Experiments on two widely used network intrusion detection benchmarks show that CausalGraph-IDS provides robust, explainable, and risk-governed detection, maintaining strong recall at low false-positive rates while delivering actionable causal insights for mitigation. © 2026 IEEE.},
note = {Journal Abbreviation: Dig Tech Pap IEEE Int Conf Consum Electron},
keywords = {Alarm systems, Budget control, causal reasoning, Chains, Computer crime, Concept Drift, Concept drifts, Conformal Risk Control, Counterfactuals, Generative AI, Human computer interaction, Intrusion Detection, Intrusion Detection Systems, Intrusion-Detection, Knowledge based systems, Language model, LLM, LLMs, Network intrusion, Network security, Risks controls, Sampling},
pubstate = {published},
tppubtype = {inproceedings}
}
Modern intrusion detection systems often achieve impressive benchmark accuracy yet fail in real-world deployment, where network behavior and attacker tactics continuously evolve. Under concept drift, decision boundaries learned offline can diverge from operational reality, triggering false-alarm cascades and creating detection blind spots that erode analyst trust. In this paper, we propose CausalGraph-IDS, a causal and language-model-assisted intrusion detection framework that moves beyond purely correlational scoring by explicitly verifying multi-stage attack chains. Additionally, we propose CHAIN-CRC, a unified algorithm that (i) learns a constrained attack-chain causal graph guided by knowledge-based priors derived from widely used adversary behavior taxonomies, (ii) computes robustness scores by testing whether alarms persist under feasible counterfactual security interventions, and (iii) applies conformal risk control to enforce operator-defined false-positive budgets with finite-sample guarantees.Generative models are integrated in strictly assistive roles through three modules: prior induction to distill causal constraints from unstructured threat reports, counterfactual generation to propose realistic and operationally feasible interventions, and causal logic justification to produce human-readable explanations grounded in the learned attack chain. Experiments on two widely used network intrusion detection benchmarks show that CausalGraph-IDS provides robust, explainable, and risk-governed detection, maintaining strong recall at low false-positive rates while delivering actionable causal insights for mitigation. © 2026 IEEE.
2.
Jalleli, O.; Zhu, Y.; Falk, T. H.
Audio-Visual Cross-Attention for Improved Deepfake Video Detection and Forgery Localization Article d'actes
Dans: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern., p. 75–79, 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: Artificial intelligence, Audio acoustics, Audio signal processing, Audio-visual, Computer vision, Crossmodal attention, Deepfake detection, Forgery, Generative AI, Localisation, Multi-modal, Video detection, Video forgeries, Visual modalities
@inproceedings{jalleliAudioVisualCrossAttentionImproved2025,
title = {Audio-Visual Cross-Attention for Improved Deepfake Video Detection and Forgery Localization},
author = {O. Jalleli and Y. Zhu and T. H. Falk},
url = {https://www.scopus.com/pages/publications/105033150623?origin=resultslist},
doi = {10.1109/SMC58881.2025.11342953},
isbn = {1062922X (ISSN); 979-833153358-8 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
pages = {75–79},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {With the emergence of multi-modal generative models, synthesized videos are becoming increasingly realistic, making the detection of deepfakes extremely challenging. While several video deepfake detection models have shown promising performance, their focus has been primarily on the visual modality. To overcome this limitation, we propose a dualstream framework that fuses visual and auditory information via cross-attention computed between embeddings extracted from pre-trained video and audio encoders. Additionally, we design a weakly-supervised forgery localization head that infers frame-level forgery scores from coarse segment-level labels, minimizing the need for fine-grained annotations and allowing for forgery location characterization. In this paper, we describe our preliminary results showing the proposed model outperforming state-of-the-art detectors on both frame-level localization and sequence-level deepfake detection tasks. Ongoing work focuses on investigating the complementarity between the visual and auditory modalities to improve model robustness and explainability. © 2025 IEEE.},
note = {Journal Abbreviation: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
keywords = {Artificial intelligence, Audio acoustics, Audio signal processing, Audio-visual, Computer vision, Crossmodal attention, Deepfake detection, Forgery, Generative AI, Localisation, Multi-modal, Video detection, Video forgeries, Visual modalities},
pubstate = {published},
tppubtype = {inproceedings}
}
With the emergence of multi-modal generative models, synthesized videos are becoming increasingly realistic, making the detection of deepfakes extremely challenging. While several video deepfake detection models have shown promising performance, their focus has been primarily on the visual modality. To overcome this limitation, we propose a dualstream framework that fuses visual and auditory information via cross-attention computed between embeddings extracted from pre-trained video and audio encoders. Additionally, we design a weakly-supervised forgery localization head that infers frame-level forgery scores from coarse segment-level labels, minimizing the need for fine-grained annotations and allowing for forgery location characterization. In this paper, we describe our preliminary results showing the proposed model outperforming state-of-the-art detectors on both frame-level localization and sequence-level deepfake detection tasks. Ongoing work focuses on investigating the complementarity between the visual and auditory modalities to improve model robustness and explainability. © 2025 IEEE.
3.
Lopes, M. K. S.; Falk, T. H.
Generative AI for Personalized Multisensory Immersive Experiences: Challenges and Opportunities for Stress Reduction Article d'actes
Dans: Proc. - IEEE Conf. Virtual Real. 3D User Interfaces Abstr. Workshops, VRW, p. 143–146, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 979-833151484-6 (ISBN), (Journal Abbreviation: Proc. - IEEE Conf. Virtual Real. 3D User Interfaces Abstr. Workshops, VRW).
Résumé | Liens | BibTeX | Étiquettes: Artificial intelligence tools, Environment personalization, Forest bathing, Generative AI, Immersive, Multi-Sensory, Multi-sensory virtual reality, Multisensory, Personalizations, relaxation, virtual reality, Virtualization
@inproceedings{lopesGenerativeAIPersonalized2025,
title = {Generative AI for Personalized Multisensory Immersive Experiences: Challenges and Opportunities for Stress Reduction},
author = {M. K. S. Lopes and T. H. Falk},
url = {https://www.scopus.com/pages/publications/105005149501?origin=resultslist},
doi = {10.1109/VRW66409.2025.00036},
isbn = {979-833151484-6 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {Proc. - IEEE Conf. Virtual Real. 3D User Interfaces Abstr. Workshops, VRW},
pages = {143–146},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Stress management and relaxation are critical areas of interest in mental health and well-being. Forest bathing is a practice that has been shown to have a positive effect on reducing stress by stimulating all the senses in an immersive nature experience. Since access to nature is not universally available to everyone, virtual reality has emerged as a promising tool to simulate this type of experience. Furthermore, generative artificial intelligence (GenAI) tools offer new opportunities to create highly personalized and immersive experiences that can enhance relaxation and reduce stress. This study explores the potential of personalized multisensory VR environments, designed using GenAI tools, to optimize relaxation and stress relief via two experiments that are currently underway. The first evaluates the effectiveness of non-personalized versus personalized VR scenes generated using AI tools to promote increased relaxation. The second explores the potential benefits of providing the user with additional personalization tools, from adding new virtual elements to the AI-generated scene, to adding AI-generated sounds and scent/haptics customization. Ultimately, this research aims to identify which customizable elements may lead to improved therapeutic benefits for multisensory VR experiences. © 2025 IEEE.},
note = {Journal Abbreviation: Proc. - IEEE Conf. Virtual Real. 3D User Interfaces Abstr. Workshops, VRW},
keywords = {Artificial intelligence tools, Environment personalization, Forest bathing, Generative AI, Immersive, Multi-Sensory, Multi-sensory virtual reality, Multisensory, Personalizations, relaxation, virtual reality, Virtualization},
pubstate = {published},
tppubtype = {inproceedings}
}
Stress management and relaxation are critical areas of interest in mental health and well-being. Forest bathing is a practice that has been shown to have a positive effect on reducing stress by stimulating all the senses in an immersive nature experience. Since access to nature is not universally available to everyone, virtual reality has emerged as a promising tool to simulate this type of experience. Furthermore, generative artificial intelligence (GenAI) tools offer new opportunities to create highly personalized and immersive experiences that can enhance relaxation and reduce stress. This study explores the potential of personalized multisensory VR environments, designed using GenAI tools, to optimize relaxation and stress relief via two experiments that are currently underway. The first evaluates the effectiveness of non-personalized versus personalized VR scenes generated using AI tools to promote increased relaxation. The second explores the potential benefits of providing the user with additional personalization tools, from adding new virtual elements to the AI-generated scene, to adding AI-generated sounds and scent/haptics customization. Ultimately, this research aims to identify which customizable elements may lead to improved therapeutic benefits for multisensory VR experiences. © 2025 IEEE.