Minimax Rates of Estimating Approximate Differential Privacy

by   Xiyang Liu, et al.
University of Washington

Differential privacy has become a widely accepted notion of privacy, leading to the introduction and deployment of numerous privatization mechanisms. However, ensuring the privacy guarantee is an error-prone process, both in designing mechanisms and in implementing those mechanisms. Both types of errors will be greatly reduced, if we have a data-driven approach to verify privacy guarantees, from a black-box access to a mechanism. We pose it as a property estimation problem, and study the fundamental trade-offs involved in the accuracy in estimated privacy guarantees and the number of samples required. We introduce a novel estimator that uses polynomial approximation of a carefully chosen degree to optimally trade-off bias and variance. With n samples, we show that this estimator achieves performance of a straightforward plug-in estimator with n n samples, a phenomenon referred to as effective sample size amplification. The minimax optimality of the proposed estimator is proved by comparing it to a matching fundamental lower bound.


Lower Bounds for Rényi Differential Privacy in a Black-Box Setting

We present new methods for assessing the privacy guarantees of an algori...

Property Testing for Differential Privacy

We consider the problem of property testing for differential privacy: wi...

On the Contractivity of Privacy Mechanisms

We present a novel way to compare the statistical cost of privacy mechan...

Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning

Achieving optimal statistical performance while ensuring the privacy of ...

Local Differential Privacy Is Equivalent to Contraction of E_γ-Divergence

We investigate the local differential privacy (LDP) guarantees of a rand...

Optimal locally private estimation under ℓ_p loss for 1< p< 2

We consider the minimax estimation problem of a discrete distribution wi...

Combining Public and Private Data

Differential privacy is widely adopted to provide provable privacy guara...

Please sign up or login with your details

Forgot password? Click here to reset