Overview
The focus of this workshop is to bring together researchers from industry and academia that focus on both distributed and privacy-preserved machine learning for vision and imaging. These topics are of increasingly large commercial and policy interest. It is therefore important to build a community for this research area, which involves collaborating researchers that share insights, code, data, benchmarks, training pipelines, etc and together aim to improve the state of privacy in computer vision. The topics of interest for this workshop include, but are not limited to:
- Notions of privacy for computer vision and imaging
- Privacy and security in other imaging modalities
- Privacy-preserving synthetic data release
- Privacy-preserving video understanding
- Privacy-Enhancing Face Biometrics
- Privacy in Medical Imaging
- Federated Learning and Split Learning
- Differential Privacy in Deep Learning and Computer Vision
- Privacy and security attacks (Model Inversion, Membership Inference etc.)
- Metrics and Benchmarks for analysing privacy risks in computer vision
- Differential privacy and other statistical notions of privacy: theory, applications, and implementations
- Hardware-based techniques for privacy-preserving ML
- Cryptographic techniques for Privacy in vision & imaging
- Policy and Compliance for Data Privacy
- Privacy, Fairness, Accountability and Transparency (F.A.T) in Machine Learning
- Applications of privacy-preserving ML
Organizers
Keynote Speakers
Call For Papers
This year, our workshop will exclusively feature only invited talks.
Agenda
All times are listed in Malmo, Sweden (CET Timezone)
(In-Person Event)
9th Sept, 2026. Room: Quality View Hotel - Stroget 3
Vivek Sharma
Opening
M. Saquib Sarfraz
Privacy Accessibility Through Foundation Model Representations
Daniel Pap, J.D.
Anchoring Human Rights in the Technological Age: The Council of Europe's Strategic Response
Kiran Bylappa Raja
Privacy Preserved Synthetic Data for Biometrics
Torsten Sattler
Privacy-preserving Visual Localization
Joan LaRovere, MD.
Talk Title: TBD
Vivek Sharma
Closing
Poster Session. Room: MalmoMassan Exhibit Hall, 241 - 260
1. HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training. Maciej Wozniak · Jesper Ericsson · Hariprasath Govindarajan · Truls Nyberg · Thomas Gustafsson · Patric Jensfelt · Olov Andersson
2. Vulnerability of Privacy-Preserving Visual Localization against Diffusion-based Attacks. Maxime Pietrantoni · Torsten Sattler · Gabriela Csurka
3. MOOZY: A Patient-First Foundation Model for Computational Pathology. Yousef Hassan · Vincent Quoc-Huy Trinh · Christopher Pal · Mahdi S. Hosseini
4. Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation. Arthème Gauthier-Villars · Guodong Ding · Angela Yao
5. NanoVSR: Towards Real-Time Video Super-Resolution on Edge Devices. Filip Pawlicki · Marcel Kańduła · Marcin Pucek · Kamil Dobies
6. Data Circuit Breaker: Identifying Training, Test, and Generated Data in Image Generative Models. Bihe Zhao · Michel Meintz · Juangui Xu · Franziska Boenisch · Adam Dziedzic
7. Defending from GeoLocalization through Adversarial Road Trips. Niccolò Niccoli · Federico Becattini · Lorenzo Seidenari
8. A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP. Hodaya Krakover · Meir Yossef Levi · Eyal Gofer · Guy Gilboa
9. InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics. Erich Liang · Caleb Kha-Uong · Chinmaya Saran · Sreemanti Dey · David Liu · Junhan Ouyang · Benjamin Zhou · Jia Deng
10. Synthetic-Trained Class-Agnostic Proposals for Foreign-Object Localization in Chest X-rays. Constantin Seibold · David Vinu · Matthias A. Fink
11. Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression. Oleksii Nasypanyi · Jaemin Cho · Utku Ozbulak · Byungkon Kang · Francois Rameau
12. Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation. Lucas Görnhardt · Timo Bartels · Niklas Schwarz · Tim Fingscheidt
13. Explainability-aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors. Chengzeng You ⋅ Binbin Xu ⋅ Soteris Demetriou
14. Learning to Generate Rigid Body Interactions with Video Diffusion Models. David Orlando Romero Mogrovejo ⋅ Ariana Bermudez ⋅ Viacheslav Iablochnikov ⋅ Hao Li ⋅ Fabio Pizzati ⋅ Ivan Laptev
15. Spectral Gradient Orthogonalization Improves Differentially Private Training at Scale. Sabari Shanmugam ⋅ Nick Barnes ⋅ Kerry Taylor