PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning

2025/10/27 by Melis, Luca, Grange, Matthew, Kalemaj, Iden +4
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2510.23427

Abstract

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.

Citations

• Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
• Auditing f-Differential Privacy in One Run
• Measuring memorization in language models via probabilistic extraction
• Range Membership Inference Attacks
• Low-Cost High-Power Membership Inference Attacks
• Scalable Extraction of Training Data from (Production) Language Models
• DP-Auditorium: a Large Scale Library for Auditing Differential Privacy
• Privacy Auditing with One (1) Training Run
• Quantifying Memorization Across Neural Language Models
• On the Importance of Difficulty Calibration in Membership Inference Attacks
• Extracting Training Data from Large Language Models
• Empirical Differential Privacy
• Membership Inference Attacks against Machine Learning Models
• Deep Residual Learning for Image Recognition
• The Composition Theorem for Differential Privacy

Related

• A General Framework for Auditing Differentially Private Machine Learning
• ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning
• Privacy-Preserving Machine Learning: Methods, Challenges and Directions
• State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey
• Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble