Interpretable DP
A suite of tools for statistics and machine learning with interpretable risk-based privacy guarantees for easy auditability and communication in regulated environments.
Technical Layer
Audience: Researchers, differential privacy experts
riskcal
Tools for computing f-DP trade-off curves for differentially private algorithms, and calibrating their noise scale to operational privacy risk measures (attack advantage, or attack TPR and FPR).
pip install riskcal
gdpnum
Tools for numerically computing the correct, non-asymptotic Gaussian Differential Privacy (GDP) guarantees for DP-SGD or similar privacy-preserving algorithms.
pip install gdpnum
Application Layer
Audience: Researchers, data scientists
risksyn
Synthetic data generation with interpretable privacy guarantees in terms of attack risk.
About
Publications
This software suite has emerged as a result of several independent scientific collaborations.
People
Funding
The effort is partially funded by the Swiss National Science Foundation (SNF):
Bridging Regulatory Data Protection Standards and Model Sharing in Healthcare