NEWS · RESEARCH · #304
Google Research releases DP-Auditorium, a Python library for black-box auditing of differential privacy
Google Research published DP-Auditorium, an open-source Python library that audits differential privacy guarantees using only black-box access to mechanisms. The library provides property testers and dataset finders (including novel HockeyStick, Rényi, and MMD testers) and demonstrates the ability to detect DP guarantee violations across multiple DP definitions (pure, approximate, Rényi).
KEY POINTS
- Google Research published DP-Auditorium, an open-source Python library that audits differential privacy guarantees using only black-box access to mechanisms.
- The library provides property testers and dataset finders (including novel HockeyStick, Rényi, and MMD testers) and demonstrates the ability to detect DP guarantee violations across multiple DP definitions (pure, approximate, Rényi).
- Practical black-box auditing tools like DP-Auditorium help detect faulty implementations or proofs of DP mechanisms, increasing trust in privacy-preserving systems used across research and industry.
WHY IT MATTERS
Practical black-box auditing tools like DP-Auditorium help detect faulty implementations or proofs of DP mechanisms, increasing trust in privacy-preserving systems used across research and industry.