Programme

Semaine Lun. 01 Mar. 02 Mer. 03 Jeu. 04 Liste

	Lun. 01	Mar. 02	Mer. 03	Jeu. 04
07:00 08:00 09:00 10:00 11:00 12:00 13:00 14:00 15:00 16:00 17:00 18:00 19:00 20:00 21:00 22:00	Accueil 17:00 - 19:30 (2h30) Accueil Accueil des participants Départ de la navette pour le Castel Ste Anne Accueil 17:25 - 17:30 (05min) Départ de la navette pour le Castel Ste Anne Départ à 17h30 de la gare de Lannion. Dîner 19:30 - 22:00 (2h30) Dîner	Petit déjeuner 7:30 - 9:00 (1h30) Petit déjeuner Keynote 1: Building Effective Privacy-Preserving Data Analytics with PrivaGym 9:00 - 10:00 (1h) Keynote 1: Building Effective Privacy-Preserving Data Analytics with PrivaGym Apostolos Pyrgelis (RISE Research Institutes of Sweden) https://apvp2026.sciencesconf.org/data/program/apostolos_pyrgelis_keynote.txt Session A1 -- Privacy vulnerabilities: data and models 10:00 - 10:40 (40min) Session A1 -- Privacy vulnerabilities: data and models Salle 1 › A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities - Aya CHERIGUI, Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies (UMR 6174), Orange Research 10:00-10:20 (20min) › Beyond the mask : The illusion of privacy in defaced brain MRI - Imen Bajar, Centre Inria de Lyon - Mohamed Maouche, Centre Inria de Lyon 10:20-10:40 (20min) Pause café 10:40 - 11:10 (30min) Pause café Session A2 -- Privacy vulnerabilities: data and models 11:10 - 12:50 (1h40) Session A2 -- Privacy vulnerabilities: data and models › Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage - Braham TALEB, EDF Labs, Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux 11:10-11:30 (20min) › Mobility Traces under Attack: How LLMs Automate Privacy and Social Engineering Attacks - Marwa EL KAMIL, Inria, Ecole de Technologie Supérieure [Montréal] 11:30-11:50 (20min) › Practical and Ready-to-Use Methodology to Assess the re-identification Risk in Anonymized Datasets - Louis Philippe Sondeck, COACHMESEC Consulting (Clever Identity) - maryline laurent, SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris 11:50-12:10 (20min) › Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies - Yasmine Hayder, Institut National des Sciences Appliquées - Centre Val de Loire, LIFO, Concevoir des technologies d'amélioration de la vie privée explicables et efficaces 12:10-12:30 (20min) › Cryptographic Traceability and Verifiability of Sensitive Security Data Before Generative AI Processing - Yulliwas AMEUR, CEDRIC. Réseaux et Objets Connectés, EFREI Paris 12:30-12:50 (20min) Déjeuner 12:50 - 14:00 (1h10) Déjeuner Table Ronde 14:00 - 15:00 (1h) Table Ronde Session B1 -- Privacy-preserving machine learning 15:00 - 15:40 (40min) Session B1 -- Privacy-preserving machine learning › Improving Unlearning with Model Updates Probably Aligned with Gradients - Virgile Dine, Centre Inria de l'Université de Rennes 15:00-15:20 (20min) › Privacy-Utility Trade-off under Rate Constraint in Federated Learning - Mamour Ndiaye, LISTIC 15:20-15:40 (20min) Pause café 15:40 - 16:10 (30min) Pause café Session B2 -- Privacy-preserving machine learning 16:10 - 17:10 (1h) Session B2 -- Privacy-preserving machine learning › Learning with Locally Private Examples by Inverse Weierstrass Private Stochastic Gradient Descent - Jean Dufraiche, MAGNET (Machine Learning in Information Networks) 16:10-16:30 (20min) › Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization - Dimitri Lerévérend, Centre Inria de l'Université de Rennes, the World Is Distributed Exploring the tension between scale and coordination 16:30-16:50 (20min) › Titre : Google, l'apprentissage fédéré et la protection de la vie privée, ou comment redéfinir un problème pour mieux l'invisibiliser. Sous-titre : Comprendre l'institution d'un cadrage par l'analyse de controverse. - Marie Garin, Centre Internet et Société 16:50-17:10 (20min) Session C -- Applied cryptography and privacy-preserving distributed algorithms 17:15 - 18:15 (1h) Session C -- Applied cryptography and privacy-preserving distributed algorithms › Opening Pandora's Box: White-Box Attacks on Microsoft's PhotoDNA Perceptual Hash Function - Diane Leblanc-Albarel, COSIC, KU Leuven 17:15-17:35 (20min) › POPPY: Scalable and Secure Spectral Centrality for Distributed Graphs via Homomorphic Encryption - Claire Guichemerre, Université de Rennes 17:35-17:55 (20min) › Giskard : Scalable Byzantine-Robust and Privacy-Preserving Decentralized Learning - Ousmane Touat, CNRS 17:55-18:15 (20min) Dîner 19:30 - 22:00 (2h30) Dîner	Petit déjeuner 7:30 - 9:00 (1h30) Petit déjeuner Keynote 2: On the Security and Privacy Risks of Browser Extensions 9:00 - 10:00 (1h) Keynote 2: On the Security and Privacy Risks of Browser Extensions Aurore Fass (INRIA Centre at Université Côte d'Azur) https://apvp2026.sciencesconf.org/data/program/Infos_talk_Aurore.txt Session D -- Web tracking through chains of redirections 10:00 - 10:40 (40min) Session D -- Web tracking through chains of redirections › QRisk: Privacy risks of URLs encoded as QR codes - Mathieu Cunche, PRIVATICS 10:00-10:20 (20min) › Gotta Catch 'em all: On the Web Tracking Practices of a Deal-Sharing Conglomerate and their Heavy Reliance on Redirect Chain - Sterenn Roux, Univ Rennes, Inria, IRISA 10:20-10:40 (20min) Pause café 10:40 - 11:10 (30min) Pause café Session E -- Online ad surveillance and regulation 11:10 - 12:30 (1h20) Session E -- Online ad surveillance and regulation › Stetoscope: underStand TargEting and manipulaTiOnS via COllaborative Private data collEction - Antoine Boutet, CITI Centre of Innovation in Telecommunications and Integration of services 11:10-11:30 (20min) › A Year Under the DSA: Ad Transparency's Uneven Landscape - Abir Benzaamia, Analyse et traitement de données complexes à grande échelle 11:30-11:50 (20min) › Privacy Settings and Ad Perception: The Shift from Third-Party Cookies to the Privacy Sandbox - Abir Benzaamia, Analyse et traitement de données complexes à grande échelle 11:50-12:10 (20min) › Are internet standard developing organisations data controllers under the GDPR? - Julien ROSSI, CEMTI - Jonathan Keller, CEMTI - Université Paris 8 12:10-12:30 (20min) Gong show 12:30 - 12:50 (20min) Gong show › [Work in Progress] Synthetic data generation for anonymization: a threshold question? Aligning Computer Science and Law for circumventing uncertainty - Mélanie Romano, IRISA 12:30-12:34 (04min) › WIP: Protecting against Membership Inference Attacks with Metric Privacy - Andreas Athanasiou, TU Delft 12:34-12:38 (04min) › La Smart City : Source de perspectives juridiques et technologiques locale, vecteur de nouveaux enjeux internationaux - Damien Franchi, Institut de l'Ouest : Droit et Europe 12:38-12:42 (04min) › Towards Context-aware Intrusion Detection in Individual-oriented Information Systems: An Empirical Study on Android Malware - 12:42-12:46 (04min) › SciReNum – La science au cœur de la régulation du numérique : co-production de politiques publiques par l'expertise scientifique au sein de la CNIL et de son écosystème - 12:46-12:50 (04min) Déjeuner 12:50 - 14:00 (1h10) Déjeuner Social event 14:00 - 18:00 (4h) Social event Surprise Cocktail dînatoire 19:30 - 22:00 (2h30) Cocktail dînatoire	Petit déjeuner 7:30 - 9:00 (1h30) Petit déjeuner Keynote 3 (coming soon) 9:00 - 10:00 (1h) Keynote 3 (coming soon) Iván Székely (Central European University) Session F -- Privacy and fairness 10:00 - 10:40 (40min) Session F -- Privacy and fairness › Impact Disproportionné en Génération de Données Synthétiques - Paul Andrey, MAGNET (Machine Learning in Information Networks) 10:00-10:20 (20min) › Attribute Inference on Differentially Private and Fair Learning - Zhan XU, Service Expérimentation et Développement Inria Lyon 10:20-10:40 (20min) Pause café 10:40 - 11:00 (20min) Pause café Session G -- Privacy-preserving data publishing: relational data, textual data, and high-dimensional data 11:00 - 12:20 (1h20) Session G -- Privacy-preserving data publishing: relational data, textual data, and high-dimensional data › SoK: An Empirical Evaluation of Differentially Private Aggregation Query Answering Frameworks in Relational Databases - Jean-François Couchot, Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies (UMR 6174) - Loïs ECOFFET, FEMTO-ST 11:00-11:20 (20min) › Formalism of SQL Queries computations to ensure differential privacy - Paul Maillard-Salin, FEMTO-ST - Loïs Ecoffet, FEMTO-ST 11:20-11:40 (20min) › Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization - Gabriel Loiseau, Centre Inria de l'Université de Lille 11:40-12:00 (20min) › Want to protect your data? Just cluster them! - Arnaud Grivet Sébert, KTH Royal Institute of Technology, Stockholm, Macquarie University 12:00-12:20 (20min) Déjeuner 12:20 - 14:00 (1h40) Déjeuner Départ de la navette pour la gare de Lannion 16:25 - 16:30 (05min) Départ de la navette pour la gare de Lannion Départ du Castel Ste Anne à 16h30.

Vie privée | Accessibilité