DeepAI AI Chat
Log In Sign Up

Precision-based attacks and interval refining: how to break, then fix, differential privacy on finite computers

07/27/2022
by   Samuel Haney, et al.
desfontain.es
0

Despite being raised as a problem over ten years ago, the imprecision of floating point arithmetic continues to cause privacy failures in the implementations of differentially private noise mechanisms. In this paper, we highlight a new class of vulnerabilities, which we call precision-based attacks, and which affect several open source libraries. To address this vulnerability and implement differentially private mechanisms on floating-point space in a safe way, we propose a novel technique, called interval refining. This technique has minimal error, provable privacy, and broad applicability. We use interval refining to design and implement a variant of the Laplace mechanism that is equivalent to sampling from the Laplace distribution and rounding to a float. We report on the performance of this approach, and discuss how interval refining can be used to implement other mechanisms safely, including the Gaussian mechanism and the exponential mechanism.

READ FULL TEXT

page 1

page 2

page 3

page 4

12/10/2021

Are We There Yet? Timing and Floating-Point Attacks on Differential Privacy Systems

Differential privacy is a de facto privacy framework that has seen adopt...
12/09/2019

Implementing the Exponential Mechanism with Base-2 Differential Privacy

Despite excellent theoretical support, Differential Privacy (DP) can sti...
07/21/2022

Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix It

We identify a new class of vulnerabilities in implementations of differe...
07/21/2021

Secure Random Sampling in Differential Privacy

Differential privacy is among the most prominent techniques for preservi...
05/25/2022

Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning

We study the privacy risks that are associated with training a neural ne...
01/08/2021

Observations on the Bias of Nonnegative Mechanisms for Differential Privacy

We study two methods for differentially private analysis of bounded data...
05/12/2021

A Statistical Threshold for Adversarial Classification in Laplace Mechanisms

This paper studies the statistical characterization of detecting an adve...