From Robustness to Privacy and Back

Understand

We study the relationship between two desiderata of algorithms in statistical inference and machine learning: differential privacy and robustness to adversarial data corruptions.

• Their conceptual similarity was first observed by Dwork and Lei (STOC 2009), who observed that private algorithms satisfy robustness, and gave a general method for converting robust algorithms to private ones.
• However, all general methods for transforming robust algorithms into private ones lead to suboptimal error rates.
• Our work gives the first black-box transformation that converts any adversarially robust algorithm into one that satisfies pure differential privacy.