Maximal Information Leakage based Privacy Preserving Data Disclosure Mechanisms

04/01/2019
by   Tianrui Xiao, et al.
0

It is often necessary to disclose training data to the public domain, while protecting privacy of certain sensitive labels. We use information theoretic measures to develop such privacy preserving data disclosure mechanisms. Our mechanism involves perturbing the data vectors in a manner that strikes a balance in the privacy-utility trade-off. We use maximal information leakage between the output data vector and the confidential label as our privacy metric. We first study the theoretical Bernoulli-Gaussian model and study the privacy-utility trade-off when only the mean of the Gaussian distributions can be perturbed. We show that the optimal solution is the same as the case when the utility is measured using probability of error at the adversary. We then consider an application of this framework to a data driven setting and provide an empirical approximation to the Sibson mutual information. By performing experiments on the MNIST and FERG data-sets, we show that our proposed framework achieves equivalent or better privacy than previous methods based on mutual information.

READ FULL TEXT

page 1

page 10

page 12

page 14

page 15

research
01/27/2023

Information-Theoretic Privacy-Preserving Schemes Based On Perfect Privacy

Consider a pair of random variables (X,Y) distributed according to a giv...
research
12/19/2017

Privacy-Preserving Adversarial Networks

We propose a data-driven framework for optimizing privacy-preserving dat...
research
10/10/2020

Data-driven Regularized Inference Privacy

Data is used widely by service providers as input to inference systems t...
research
04/05/2021

Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics

With the growing use of camera devices, the industry has many image data...
research
01/17/2023

Binary Mechanisms under Privacy-Preserving Noise

We study mechanism design for public-good provision under a noisy privac...
research
09/13/2020

Information Laundering for Model Privacy

In this work, we propose information laundering, a novel framework for e...
research
09/09/2020

On Perfect Obfuscation: Local Information Geometry Analysis

We consider the problem of privacy-preserving data release for a specifi...

Please sign up or login with your details

Forgot password? Click here to reset