Privacy for Vision & Imaging

2nd International Workshop

In Conjunction with ECCV 2024, Milan, Italy



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

Call For Papers

This year, our workshop will exclusively feature only invited talks.

Agenda

All times are listed in Milan, Italy (CET Timezone)

(In-Person Event)

29 Sept, 2024. Room: Suite 4
9:00am

Vivek Sharma

Opening

Intro: Decentralized AI, MIT Media Lab

9:10am

Carlos Hinojosa

Privacy-preserving in Computer Vision through Optics Learning

9:40am

Gabriele Mazzini

The EU approach to AI regulation

10:10am

Amir Zamir

How far can a 1-pixel camera go?

10:40am

Marc Pollefeys

Privacy-preserving Localization and Mapping

11:10-13:00 Hrs

Poster Session. Room: Suite 4

Masked Differential Privacy. David Schneider, Sina Sajadmanesh, Vikash Sehwag, Saquib Sarfraz, Rainer Stiefelhagen, Lingjuan Lyu, Vivek Sharma
Preserving Data Confidentiality in Semiconductor Chip Design and Manufacturing in the age of AI. Greta Chiaravalli, Andrea Bonetti, Vamsi Spandan Arza, Lorenzo Servadei
Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection? Rosario Leonardi, Antonino Furnari, Francesco Ragusa, Giovanni Maria Farinella
Label-free Neural Semantic Image Synthesis. Jiayi Wang, Kevin Alexander Laube, Yumeng Li, Jan Hendrik Metzen, Shin-I Cheng, Julio Borges, Anna Khoreva
Synthesizing Environment-Specific People in Photographs. Mirela Ostrek, Carol O'Sullivan, Michael J. Black, Justus Thies
Reliability in Semantic Segmentation: Can We Use Synthetic Data? Thibaut Loiseau, Tuan-Hung Vu, Mickael Chen, Patrick Pérez, Matthieu Cord
Unveiling Privacy Risks in Stochastic Neural Networks Training: Effective Image Reconstruction from Gradients. Yiming Chen, Xiangyu Yang, Nikos Deligiannis
Privacy-Preserving Adaptive Re-Identification without Image Transfer. Hamza Rami, Jhony H. Giraldo, Nicolas Winckler, Stéphane Lathuilière
DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images. Zaid Tasneem, Akshat Dave, Abhishek Singh, Kushagra Tiwary, Praneeth Vepakomma, Ashok Veeraraghavan, Ramesh Raskar
Learning a Dynamic Privacy-preserving Camera Robust to Inversion Attacks. Jiacheng Cheng, Xiang Dai, Jia Wan, Nick Antipa, and Nuno Vasconcelos
Towards Synthetic Data Generation for Improved Pain Recognition in Videos under Patient Constraints. Jonas Nasimzada, Jens Kleesiek, Ken Herrmann, Alina Roitberg and Constantin Seibold
SIMBA: Split Inference - Mechanisms, Benchmarks and Attacks. Abhishek Singh, Vivek Sharma, Rohan Sukumaran, John Mose, Jeffrey Chiu, Justin Yu, Ramesh Raskar