From Robustness to Privacy and Back
Jul 24, 2023
Speakers
Lydia Zakynthinou
Speaker · 0 followers
Jonathan Ullman
Speaker · 0 followers
About
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. Moreover, we show that for any low-dimensional estimation task, applying our transformation to an optimal robust estimator results in an optimal private estimator. Thus, we conclude that for any low-dimensional task, the optimal error rate for ε-differentially private estimators is essentially the same as the optimal error rate for estimators that are robust to adversarially corrupting 1/ε training samples. We apply our transformation to obtain new optimal private estimators for several high-dimensional statistical tasks, including Gaussian linear regression and PCA. Finally, we present an extension of our transformation that leads to approximately differentially private algorithms whose error does not depend on the range of the output space, which is impossible under pure differential privacy.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…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Pre-training for Speech Translation: CTC Meets Optimal Transport
Watch later
Towards Explaining Distribution Shifts
Watch later
Omega: Optimistic EMA Gradients
Watch later
Juan Ramirez, …
How Can Neuroscience Help Us Build More Robust Deep Neural Networks?
Watch later
Raising the Cost of Malicious AI-Powered Image Editing
Watch later
Hadi Salman, …
