PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning
This provides a practical tool for researchers and practitioners in sensitive domains to audit privacy in ML models, though it is incremental as it builds on existing attacks and metrics.
The authors tackled the problem of assessing privacy risks in machine learning models by developing PrivacyGuard, a modular framework for empirical differential privacy analysis, which implements a suite of privacy attacks and measurement techniques to evaluate these risks.
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.