The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis, designed to evaluate privacy risks in ML models through state-of-the-art inference attacks and advanced privacy measurement techniques. To this end, PrivacyGuard implements a diverse suite of privacy attack -- including membership inference , extraction, and reconstruction attacks -- enabling both off-the-shelf and highly configurable privacy analyses. Its modular architecture allows for the seamless integration of new attacks, and privacy metrics, supporting rapid adaptation to emerging research advances. We make PrivacyGuard available at https://github.com/facebookresearch/PrivacyGuard.
@article{arxiv.2510.23427,
title = {PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning},
author = {Luca Melis and Matthew Grange and Iden Kalemaj and Karan Chadha and Shengyuan Hu and Elena Kashtelyan and Will Bullock},
journal= {arXiv preprint arXiv:2510.23427},
year = {2025}
}