Optimal Differential Privacy Composition for Exponential Mechanisms and the Cost of Adaptivity

09/30/2019
by   Jinshuo Dong, et al.
0

Composition is one of the most important properties of differential privacy (DP), as it allows algorithm designers to build complex private algorithms from DP primitives. We consider precise composition bounds of the overall privacy loss for exponential mechanisms, one of the fundamental classes of mechanisms in DP. We give explicit formulations of the optimal privacy loss for both the adaptive and non-adaptive settings. For the non-adaptive setting in which each mechanism has the same privacy parameter, we give an efficiently computable formulation of the optimal privacy loss. Furthermore, we show that there is a difference in the privacy loss when the exponential mechanism is chosen adaptively versus non-adaptively. To our knowledge, it was previously unknown whether such a gap existed for any DP mechanisms with fixed privacy parameters, and we demonstrate the gap for a widely used class of mechanism in a natural setting. We then improve upon the best previously known upper bounds for adaptive composition of exponential mechanisms with efficiently computable formulations and show the improvement.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/15/2020

Unifying Privacy Loss Composition for Data Analytics

Differential privacy (DP) provides rigorous privacy guarantees on indivi...
07/19/2022

Composition Theorems for Interactive Differential Privacy

An interactive mechanism is an algorithm that stores a data set and answ...
03/10/2022

Fully Adaptive Composition in Differential Privacy

Composition is a key feature of differential privacy. Well-known advance...
05/06/2022

Privacy accounting εconomics: Improving differential privacy composition via a posteriori bounds

Differential privacy (DP) is a widely used notion for reasoning about pr...
08/20/2022

The Saddle-Point Accountant for Differential Privacy

We introduce a new differential privacy (DP) accountant called the saddl...
08/02/2021

Privacy-Aware Rejection Sampling

Differential privacy (DP) offers strong theoretical privacy guarantees, ...
03/09/2018

The Trade-off between Privacy and Fidelity via Ehrhart Theory

As an increasing amount of data is gathered nowadays and stored in datab...