DeepAI AI Chat
Log In Sign Up

Free Gap Information from the Differentially Private Sparse Vector and Noisy Max Mechanisms

04/29/2019
by   Zeyu Ding, et al.
0

Noisy Max and Sparse Vector are selection algorithms for differential privacy and serve as building blocks for more complex algorithms. In this paper we show that both algorithms can release additional information for free (i.e., at no additional privacy cost). Noisy Max is used to return the approximate maximizer among a set of queries. We show that it can also release for free the noisy gap between the approximate maximizer and runner-up. Sparse Vector is used to return a set of queries that are approximately larger than a fixed threshold. We show that it can adaptively control its privacy budget (use less budget for queries that are likely to be much larger than the threshold) and simultaneously release for free a noisy gap between the selected queries and the threshold. It has long been suspected that Sparse Vector can release additional information, but prior attempts had incorrect proofs. Our version is proved using randomness alignment, a proof template framework borrowed from the program verification literature. We show how the free extra information in both mechanisms can be used to improve the utility of differentially private algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

12/02/2020

Free Gap Estimates from the Exponential Mechanism, Sparse Vector, Noisy Max and Related Algorithms

Private selection algorithms, such as the Exponential Mechanism, Noisy M...
09/03/2022

Differential Privacy on Dynamic Data

A fundamental problem in differential privacy is to release a privatized...
12/10/2020

Research Challenges in Designing Differentially Private Text Generation Mechanisms

Accurately learning from user data while ensuring quantifiable privacy g...
03/28/2019

Proving Differential Privacy with Shadow Execution

Recent work on formal verification of differential privacy shows a trend...
05/10/2019

Practical Differentially Private Top-k Selection with Pay-what-you-get Composition

We study the problem of top-k selection over a large domain universe sub...
11/30/2022

Answering Private Linear Queries Adaptively using the Common Mechanism

When analyzing confidential data through a privacy filter, a data scient...
03/30/2022

Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE

We provide an end-to-end Renyi DP based-framework for differentially pri...