Optimal Guarantees for Auditing R\'enyi Differentially Private Machine Learning
Researchers have developed a new auditing framework for machine learning algorithms that claim Rényi differential privacy (RDP). This framework uses the Donsker-Varadhan (DV) estimator to directly measure Rényi divergence, providing explicit confidence intervals for RDP auditing. The proposed method achieves information-theoretically optimal sample-complexity guarantees and shows empirical improvements over existing black-box methods, particularly for challenging small and moderate Rényi orders. AI
IMPACT Establishes new optimal guarantees for auditing privacy in ML models, potentially improving trust and security in deployed systems.