English

Decouple-and-Sample: Protecting sensitive information in task agnostic data release

Cryptography and Security 2022-03-25 v1 Computer Vision and Pattern Recognition Computers and Society Machine Learning

Abstract

We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in various applications of computer vision, its impact is mostly realized when data sharing is not inhibited by privacy concerns. We alleviate these concerns by sanitizing datasets in a two-stage process. First, we introduce a global decoupling stage for decomposing raw data into sensitive and non-sensitive latent representations. Secondly, we design a local sampling stage to synthetically generate sensitive information with differential privacy and merge it with non-sensitive latent features to create a useful representation while preserving the privacy. This newly formed latent information is a task-agnostic representation of the original dataset with anonymized sensitive information. While most algorithms sanitize data in a task-dependent manner, a few task-agnostic sanitization techniques sanitize data by censoring sensitive information. In this work, we show that a better privacy-utility trade-off is achieved if sensitive information can be synthesized privately. We validate the effectiveness of the sanitizer by outperforming state-of-the-art baselines on the existing benchmark tasks and demonstrating tasks that are not possible using existing techniques.

Keywords

Cite

@article{arxiv.2203.13204,
  title  = {Decouple-and-Sample: Protecting sensitive information in task agnostic data release},
  author = {Abhishek Singh and Ethan Garza and Ayush Chopra and Praneeth Vepakomma and Vivek Sharma and Ramesh Raskar},
  journal= {arXiv preprint arXiv:2203.13204},
  year   = {2022}
}

Comments

Preprint

R2 v1 2026-06-24T10:24:56.796Z