Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Shangwe, C. N.; Davoust, A.; Khoury, R.
Beyond Detection: Evaluating LLMs’ Semantic Understanding of Code Vulnerabilities Proceedings Article
In: K., Adi; O., Nguena Timo; N., Boulahia-Cuppens; D., Espes; N., Stakhanova; M., Omar (Ed.): Lect. Notes Comput. Sci., pp. 19–34, 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: Analysis workflow, Code Semantics, Codes (symbols), Critical questions, Development workflow, Interpretability, Language model, Large language model, Large Language Models (LLMs), Model semantics, Pattern matching, Semantics, Semantics understanding, Software design, Vulnerability detection
@inproceedings{shangweDetectionEvaluatingLLMs2026,
title = {Beyond Detection: Evaluating LLMs’ Semantic Understanding of Code Vulnerabilities},
author = {C. N. Shangwe and A. Davoust and R. Khoury},
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/105046105995?origin=resultslist},
doi = {10.1007/978-3-032-20732-6_2},
isbn = {03029743 (ISSN); 978-303220731-9 (ISBN)},
year = {2026},
date = {2026-01-01},
booktitle = {Lect. Notes Comput. Sci.},
volume = {16295 LNCS},
pages = {19–34},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {As Large Language Models (LLMs) become increasingly integrated into software development and analysis workflows, a critical question arises: do these models truly understand the semantics of code, or do they merely excel at pattern matching? Our goal is to assess the extent to which LLMs can back their predictions in vulnerability detection by correctly attributing the identified vulnerabilities to the violation of particular rules as proof that their decision is based on actual code semantics understanding. We employed the SVEN dataset, composed of function-level code snippets, to conduct a series of experiments that evaluate both the model’s ability to detect vulnerabilities and attribute predictions to the correct violated rule and measure LLMs’ performance under varying experimental setups. Our findings reveal that while LLMs achieve reasonable accuracy in vulnerability detection, a significant drop in performance is observed when correct rule attribution is also required, exposing a gap between perceived accuracy and actual accuracy. The difference between actual and perceived accuracy offers critical insight into the depth of code semantics understanding of LLMs in vulnerability detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.},
note = {Journal Abbreviation: Lect. Notes Comput. Sci.},
keywords = {Analysis workflow, Code Semantics, Codes (symbols), Critical questions, Development workflow, Interpretability, Language model, Large language model, Large Language Models (LLMs), Model semantics, Pattern matching, Semantics, Semantics understanding, Software design, Vulnerability detection},
pubstate = {published},
tppubtype = {inproceedings}
}
As Large Language Models (LLMs) become increasingly integrated into software development and analysis workflows, a critical question arises: do these models truly understand the semantics of code, or do they merely excel at pattern matching? Our goal is to assess the extent to which LLMs can back their predictions in vulnerability detection by correctly attributing the identified vulnerabilities to the violation of particular rules as proof that their decision is based on actual code semantics understanding. We employed the SVEN dataset, composed of function-level code snippets, to conduct a series of experiments that evaluate both the model’s ability to detect vulnerabilities and attribute predictions to the correct violated rule and measure LLMs’ performance under varying experimental setups. Our findings reveal that while LLMs achieve reasonable accuracy in vulnerability detection, a significant drop in performance is observed when correct rule attribution is also required, exposing a gap between perceived accuracy and actual accuracy. The difference between actual and perceived accuracy offers critical insight into the depth of code semantics understanding of LLMs in vulnerability detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
2.
Allili, M. S.; Ziou, D.
Adaptive appearance model for object contour tracking in videos Proceedings Article
In: Proceedings - Fourth Canadian Conference on Computer and Robot Vision, CRV 2007, pp. 510–517, Montreal, QC, 2007, ISBN: 0769527868 (ISBN); 978-076952786-4 (ISBN), (Journal Abbreviation: Proc. Fourth Can. Conf. Comput. Robot Vis.).
Abstract | Links | BibTeX | Tags: Adaptive parametric mixture models, Adaptive systems, Boundary, Color, Geometry, Image communication systems, Level sets, Level-sets, Mathematical models, Mixture of pdfs, Object mixture modelss, Pattern matching, Shape, Target tracking, Texture, Tracking, Variational techniques, Video sequences, Video signal processing
@inproceedings{allili_adaptive_2007,
title = {Adaptive appearance model for object contour tracking in videos},
author = {M. S. Allili and D. Ziou},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-34548723968&doi=10.1109%2fCRV.2007.9&partnerID=40&md5=c10008163f7f45f743ef0dcb13444c72},
doi = {10.1109/CRV.2007.9},
isbn = {0769527868 (ISBN); 978-076952786-4 (ISBN)},
year = {2007},
date = {2007-01-01},
booktitle = {Proceedings - Fourth Canadian Conference on Computer and Robot Vision, CRV 2007},
pages = {510–517},
address = {Montreal, QC},
abstract = {In this paper, we propose a novel object tracking algorithm in video sequences. The formulation of the object tracking is based on variational calculus, where an adaptive parametric mixture model is used for object features representation. The tracking is based on matching the object mixture models between successive frames of the sequence by using active contours while adapting the mixture model to varying object appearance changes due to illumination conditions and camera geometry. The implementation of the method is based on level set active contours which allow for automatic topology changes and stable numerical schemes. We validate our approach on examples of object tracking performed on real video sequences. © 2007 IEEE.},
note = {Journal Abbreviation: Proc. Fourth Can. Conf. Comput. Robot Vis.},
keywords = {Adaptive parametric mixture models, Adaptive systems, Boundary, Color, Geometry, Image communication systems, Level sets, Level-sets, Mathematical models, Mixture of pdfs, Object mixture modelss, Pattern matching, Shape, Target tracking, Texture, Tracking, Variational techniques, Video sequences, Video signal processing},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we propose a novel object tracking algorithm in video sequences. The formulation of the object tracking is based on variational calculus, where an adaptive parametric mixture model is used for object features representation. The tracking is based on matching the object mixture models between successive frames of the sequence by using active contours while adapting the mixture model to varying object appearance changes due to illumination conditions and camera geometry. The implementation of the method is based on level set active contours which allow for automatic topology changes and stable numerical schemes. We validate our approach on examples of object tracking performed on real video sequences. © 2007 IEEE.
3.
Allili, M. S.; Ziou, D.
Adaptive appearance model for object contour tracking in videos Proceedings Article
In: Proceedings - Fourth Canadian Conference on Computer and Robot Vision, CRV 2007, pp. 510–517, Montreal, QC, 2007, ISBN: 0769527868 (ISBN); 978-076952786-4 (ISBN), (Journal Abbreviation: Proc. Fourth Can. Conf. Comput. Robot Vis.).
Abstract | Links | BibTeX | Tags: Adaptive parametric mixture models, Adaptive systems, Boundary, Color, Geometry, Image communication systems, Level sets, Level-sets, Mathematical models, Mixture of pdfs, Object mixture modelss, Pattern matching, Shape, Target tracking, Texture, Tracking, Variational techniques, Video sequences, Video signal processing
@inproceedings{alliliAdaptiveAppearanceModel2007,
title = {Adaptive appearance model for object contour tracking in videos},
author = {M. S. Allili and D. Ziou},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-34548723968&doi=10.1109%2fCRV.2007.9&partnerID=40&md5=c10008163f7f45f743ef0dcb13444c72},
doi = {10.1109/CRV.2007.9},
isbn = {0769527868 (ISBN); 978-076952786-4 (ISBN)},
year = {2007},
date = {2007-01-01},
booktitle = {Proceedings - Fourth Canadian Conference on Computer and Robot Vision, CRV 2007},
pages = {510–517},
address = {Montreal, QC},
abstract = {In this paper, we propose a novel object tracking algorithm in video sequences. The formulation of the object tracking is based on variational calculus, where an adaptive parametric mixture model is used for object features representation. The tracking is based on matching the object mixture models between successive frames of the sequence by using active contours while adapting the mixture model to varying object appearance changes due to illumination conditions and camera geometry. The implementation of the method is based on level set active contours which allow for automatic topology changes and stable numerical schemes. We validate our approach on examples of object tracking performed on real video sequences. © 2007 IEEE.},
note = {Journal Abbreviation: Proc. Fourth Can. Conf. Comput. Robot Vis.},
keywords = {Adaptive parametric mixture models, Adaptive systems, Boundary, Color, Geometry, Image communication systems, Level sets, Level-sets, Mathematical models, Mixture of pdfs, Object mixture modelss, Pattern matching, Shape, Target tracking, Texture, Tracking, Variational techniques, Video sequences, Video signal processing},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we propose a novel object tracking algorithm in video sequences. The formulation of the object tracking is based on variational calculus, where an adaptive parametric mixture model is used for object features representation. The tracking is based on matching the object mixture models between successive frames of the sequence by using active contours while adapting the mixture model to varying object appearance changes due to illumination conditions and camera geometry. The implementation of the method is based on level set active contours which allow for automatic topology changes and stable numerical schemes. We validate our approach on examples of object tracking performed on real video sequences. © 2007 IEEE.
4.
Allili, M. S.; Ziou, D.
Object contour tracking in videos by matching finite mixture models Proceedings Article
In: Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006, Sydney, NSW, 2006, ISBN: 0-7695-2688-8 978-0-7695-2688-1.
Abstract | Links | BibTeX | Tags: Boundary conditions, Color image processing, Contour measurement, Finite mixture models, Image analysis, Level sets, Object contour tracking, Pattern matching, Shape information, Video signal processing
@inproceedings{allili_object_2006,
title = {Object contour tracking in videos by matching finite mixture models},
author = {M. S. Allili and D. Ziou},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-34547433254&doi=10.1109%2fAVSS.2006.83&partnerID=40&md5=aeed9598e325243f03c379766e7ac32c},
doi = {10.1109/AVSS.2006.83},
isbn = {0-7695-2688-8 978-0-7695-2688-1},
year = {2006},
date = {2006-01-01},
booktitle = {Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006},
address = {Sydney, NSW},
abstract = {In this paper, we propose a novel object tracking algorithm in video sequences. The method is based on object mixture matching between successive frames of the sequence by using active contours. Only the segmentation of the objects in the first frame is required for initialization. The evolution of the object contour on a current frame aims to find the maximum fidelity of the mixture likelihood for the same object between successive frames while having the best fit of the mixture parameters to the homogenous parts of the objects. To permit for a precise and robust tracking, region, boundary and shape information are coupled in the model. The method permits for tracking multi-class objects on cluttered and non-static backgrounds. We validate our approach on examples of tracking performed on real video sequences. © 2006 IEEE.},
keywords = {Boundary conditions, Color image processing, Contour measurement, Finite mixture models, Image analysis, Level sets, Object contour tracking, Pattern matching, Shape information, Video signal processing},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we propose a novel object tracking algorithm in video sequences. The method is based on object mixture matching between successive frames of the sequence by using active contours. Only the segmentation of the objects in the first frame is required for initialization. The evolution of the object contour on a current frame aims to find the maximum fidelity of the mixture likelihood for the same object between successive frames while having the best fit of the mixture parameters to the homogenous parts of the objects. To permit for a precise and robust tracking, region, boundary and shape information are coupled in the model. The method permits for tracking multi-class objects on cluttered and non-static backgrounds. We validate our approach on examples of tracking performed on real video sequences. © 2006 IEEE.
5.
Allili, M. S.; Ziou, D.
Object contour tracking in videos by matching finite mixture models Proceedings Article
In: Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006, Sydney, NSW, 2006, ISBN: 0-7695-2688-8 978-0-7695-2688-1.
Abstract | Links | BibTeX | Tags: Boundary conditions, Color image processing, Contour measurement, Finite mixture models, Image analysis, Level sets, Object contour tracking, Pattern matching, Shape information, Video signal processing
@inproceedings{alliliObjectContourTracking2006,
title = {Object contour tracking in videos by matching finite mixture models},
author = {M. S. Allili and D. Ziou},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-34547433254&doi=10.1109%2fAVSS.2006.83&partnerID=40&md5=aeed9598e325243f03c379766e7ac32c},
doi = {10.1109/AVSS.2006.83},
isbn = {0-7695-2688-8 978-0-7695-2688-1},
year = {2006},
date = {2006-01-01},
booktitle = {Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006},
address = {Sydney, NSW},
abstract = {In this paper, we propose a novel object tracking algorithm in video sequences. The method is based on object mixture matching between successive frames of the sequence by using active contours. Only the segmentation of the objects in the first frame is required for initialization. The evolution of the object contour on a current frame aims to find the maximum fidelity of the mixture likelihood for the same object between successive frames while having the best fit of the mixture parameters to the homogenous parts of the objects. To permit for a precise and robust tracking, region, boundary and shape information are coupled in the model. The method permits for tracking multi-class objects on cluttered and non-static backgrounds. We validate our approach on examples of tracking performed on real video sequences. © 2006 IEEE.},
keywords = {Boundary conditions, Color image processing, Contour measurement, Finite mixture models, Image analysis, Level sets, Object contour tracking, Pattern matching, Shape information, Video signal processing},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we propose a novel object tracking algorithm in video sequences. The method is based on object mixture matching between successive frames of the sequence by using active contours. Only the segmentation of the objects in the first frame is required for initialization. The evolution of the object contour on a current frame aims to find the maximum fidelity of the mixture likelihood for the same object between successive frames while having the best fit of the mixture parameters to the homogenous parts of the objects. To permit for a precise and robust tracking, region, boundary and shape information are coupled in the model. The method permits for tracking multi-class objects on cluttered and non-static backgrounds. We validate our approach on examples of tracking performed on real video sequences. © 2006 IEEE.