Publications of the team as recorded on HAL
26 documents
Journal articles
- Teddy Furon. On the Vulnerability of Retrieval in High Intrinsic Dimensionality Neighborhood. IEEE Transactions on Information Forensics and Security, In press, pp.1-1. ⟨10.1109/TIFS.2025.3553067⟩. ⟨hal-05012282⟩
- Marzieh Gheisari, Javad Amirian, Teddy Furon, Laurent Amsaleg. AggNet: Learning to aggregate faces for group membership verification. Signal Processing: Image Communication, 2024, 132, pp.117237. ⟨10.1016/j.image.2024.117237⟩. ⟨hal-04875732⟩
- Quentin Le Roux, Eric Bourbao, Yannick Teglia, Kassem Kallas. A Comprehensive Survey on Backdoor Attacks and Their Defenses in Face Recognition Systems. IEEE Access, 2024, 12, pp.47433-47468. ⟨10.1109/ACCESS.2024.3382584⟩. ⟨hal-04850549⟩
Conference papers
- Louis Hémadou, Héléna Vorobieva, Ahmed Nasreddine Benaichouche, Frédéric Jurie, Ewa Kijak. Cross-task knowledge distillation for few-shot detection. ICCV 2025 - International Conference on Computer Vision, Oct 2025, Honolulu Hawaii, United States. ⟨hal-05268562⟩
- Ryan Webster, Teddy Furon. Multi-modal Identity Extraction. ICCV 2025 - International Conference on Computer Vision, Oct 2025, Honololu, Hawaii, United States. pp.1-9. ⟨hal-05168368⟩
- Odysseas Drosis, Jade Garcia Bourrée, Anne-Marie Kermarrec, Erwan Le Merrer, Othmane Safsafi. Robust Fingerprinting of Graphs with FING. SRDS 2025 - Symposium on Reliable Distributed Systems, Sep 2025, Porto, Portugal. ⟨hal-05267625⟩
- Jade Garcia Bourrée, Hadrien Lautraite, Sébastien Gambs, Gilles Tredan, Erwan Le Merrer, et al.. P2NIA: Privacy-Preserving Non-Iterative Auditing. ECML-PKDD 2025 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2025, Porto, Portugal. ⟨10.48550/arXiv.2504.00874⟩. ⟨hal-05268379⟩
- Quentin Le Roux, Yannick Teglia, Eric Bourbao, Philippe Loubet-Moundi, Teddy Furon. BAIT: A new dnn backdoor attack using inpainted triggers. ICIP 2025 - IEEE International Conference on Image Processing, Sep 2025, Anchorage (AK), United States. pp.1-6. ⟨hal-05168358⟩
- Jade Garcia Bourrée, Augustin Godinot, Sayan Biswas, Anne-Marie Kermarrec, Erwan Le Merrer, et al.. Robust ML Auditing using Prior Knowledge. ICML 2025 - 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada. ⟨10.48550/arXiv.2505.04796⟩. ⟨hal-05268400⟩
- Brian Pufler, Yury Belousov, Vitaliy Kinakh, Teddy Furon, Slava Voloshynovskiy. Task-Agnostic Attacks Against Vision Foundation Models. 5th Workshop of Adversarial Machine Learning at CVPR 2025, Jun 2025, Nashville, United States. pp.1-18. ⟨hal-05172315⟩
- Jade Garcia Bourrée, Anne-Marie Kermarrec, Erwan Le Merrer, Othmane Safsafi. Fast & Fourier: tatouage spectral de graphes. ALGOTEL 2025 – 27èmes Rencontres Francophones sur les Aspects Algorithmiques des Télécommunications, Jun 2025, Saint Valery-sur-Somme, France. pp.1-5. ⟨hal-05016042⟩
- Tom Sander, Pierre Fernandez, Alain Durmus, Teddy Furon, Matthijs Douze. Watermark anything with localized messages. International Conference on Learning Representations - ICLR 2025, Apr 2025, Singapour, Singapore. ⟨hal-04970818⟩
- Chloé Imadache, Eva Giboulot, Teddy Furon. Evaluating the security of public surrogate watermark detectors. ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2025, Hyderabad, India. pp.1-5, ⟨10.1109/ICASSP49660.2025.10889821⟩. ⟨hal-05168353⟩
- Louis Hémadou, Héléna Vorobieva, Ewa Kijak, Frédéric Jurie. Adapting Without Seeing: Text-Aided Domain Adaptation for Adapting CLIP-like Models to Novel Domains. IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2025, Hyderabad, India. ⟨hal-04889885⟩
- Augustin Godinot, Erwan Le Merrer, Camilla Penzo, François Taïani, Gilles Tredan. Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes. AAAI 2025 - 39th Annual AAAI Conference on Artificial Intelligence, Feb 2025, Philadelphia (Pennsylvania), United States. pp.16817-16825, ⟨10.1609/aaai.v39i16.33848⟩. ⟨hal-05093903⟩
- Gautier Evennou, Antoine Chaffin, Vivien Chappelier, Ewa Kijak. Reframing Image Difference Captioning with BLIP2IDC and Synthetic Augmentation. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Feb 2025, Tucson (Arizona ), United States. ⟨hal-04889899⟩
- Tom Sander, Pierre Fernandez, Alain Durmus, Matthijs Douze, Teddy Furon. Watermarking Makes Language Models Radioactive. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. pp.1-35. ⟨hal-04766621⟩
- Eva Giboulot, Teddy Furon. WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada. pp.1-34. ⟨hal-04766606⟩
- Erwan Le Merrer, Gilles Trédan. LLMs hallucinate graphs too: a structural perspective. complex networks 2024, Dec 2024, Istanbul, Turkey. ⟨hal-04684742⟩
- Gautier Evennou, Vivien Chappelier, Ewa Kijak, Teddy Furon. SWIFT: Semantic Watermarking for Image Forgery Thwarting. WIFS 2024 - 16th IEEE International Workshop on Information Forensics and Security, IEEE, Dec 2024, Roma, Italy. pp.1-6. ⟨hal-04728070⟩
- Enoal Gesny, Eva Giboulot, Teddy Furon. When does gradient estimation improve black-box adversarial attacks?. WIFS 2024 -16th IEEE International Workshop on Information Forensics and Security, Dec 2024, Roma, Italy. pp.1-6. ⟨hal-04728275⟩
- Martijn de Vos, Akash Dhasade, Jade Garcia Bourrée, Anne-Marie Kermarrec, Erwan Le Merrer, et al.. Fairness Auditing with Multi-Agent Collaboration. 27th European Conference on Artificial Intelligence (ECAI 2024), Oct 2024, Santiago de Compostela, Spain. pp.1-14, ⟨10.3233/FAIA240604⟩. ⟨hal-04800328⟩
- Quentin Le Roux, Kassem Kallas, Teddy Furon. A Double-Edged Sword: The Power of Two in Defending Against DNN Backdoor Attacks. EUSIPCO 2024 - 32nd IEEE European Signal Processing Conference, Aug 2024, Lyon, France. pp.2007-2011, ⟨10.23919/EUSIPCO63174.2024.10715340⟩. ⟨hal-04850574⟩
- Louis Hémadou, Héléna Vorobieva, Ewa Kijak, Frédéric Jurie. Beyond Internet Images: Evaluating Vision-Language Models for Domain Generalization on Synthetic-to-Real Industrial Datasets. Synthetic Data for Computer Vision - CVPR 2024, Jun 2024, Seattle, Washington, United States. pp.1-6. ⟨hal-04889782⟩
- Augustin Godinot, Erwan Le Merrer, Gilles Trédan, Camilla Penzo, François Taïani. Under manipulations, are some AI models harder to audit?. 2nd IEEE Conference on Secure and Trustworthy Machine Learning (SaTML 2024), Apr 2024, Toronto ( CA ), Canada. pp.1-21. ⟨hal-04800332⟩
Preprints, Working Papers
- Quentin Le Roux, Yannick Teglia, Teddy Furon, Philippe Loubet-Moundi, Eric Bourbao. Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems. 2025. ⟨hal-05168341⟩
Powered by HAL 
