KNG: The K-Norm Gradient Mechanism

05/23/2019
by   Matthew Reimherr, et al.
0

This paper presents a new mechanism for producing sanitized statistical summaries that achieve differential privacy, called the K-Norm Gradient Mechanism, or KNG. This new approach maintains the strong flexibility of the exponential mechanism, while achieving the powerful utility performance of objective perturbation. KNG starts with an inherent objective function (often an empirical risk), and promotes summaries that are close to minimizing the objective by weighting according to how far the gradient of the objective function is from zero. Working with the gradient instead of the original objective function allows for additional flexibility as one can penalize using different norms. We show that, unlike the exponential mechanism, the noise added by KNG is asymptotically negligible compared to the statistical error for many problems. In addition to theoretical guarantees on privacy and utility, we confirm the utility of KNG empirically in the settings of linear and quantile regression through simulations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/30/2019

Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA

The exponential mechanism is a fundamental tool of Differential Privacy ...
research
11/11/2019

Achieving Differential Privacy in Vertically Partitioned Multiparty Learning

Preserving differential privacy has been well studied under centralized ...
research
09/21/2022

Shape And Structure Preserving Differential Privacy

It is common for data structures such as images and shapes of 2D objects...
research
06/20/2017

Statistical Mechanics of Node-perturbation Learning with Noisy Baseline

Node-perturbation learning is a type of statistical gradient descent alg...
research
10/08/2020

Duff: A Dataset-Distance-Based Utility Function Family for the Exponential Mechanism

We propose and analyze a general-purpose dataset-distance-based utility ...
research
04/03/2022

Exact Privacy Guarantees for Markov Chain Implementations of the Exponential Mechanism with Artificial Atoms

Implementations of the exponential mechanism in differential privacy oft...

Please sign up or login with your details

Forgot password? Click here to reset