DeepAI AI Chat
Log In Sign Up

Learning to Noise: Application-Agnostic Data Sharing with Local Differential Privacy

by   Alex Mansbridge, et al.

In recent years, the collection and sharing of individuals' private data has become commonplace in many industries. Local differential privacy (LDP) is a rigorous approach which uses a randomized algorithm to preserve privacy even from the database administrator, unlike the more standard central differential privacy. For LDP, when applying noise directly to high-dimensional data, the level of noise required all but entirely destroys data utility. In this paper we introduce a novel, application-agnostic privatization mechanism that leverages representation learning to overcome the prohibitive noise requirements of direct methods, while maintaining the strict guarantees of LDP. We further demonstrate that this privatization mechanism can be used to train machine learning algorithms across a range of applications, including private data collection, private novel-class classification, and the augmentation of clean datasets with additional privatized features. We achieve significant gains in performance on downstream classification tasks relative to benchmarks that noise the data directly, which are state-of-the-art in the context of application-agnostic LDP mechanisms for high-dimensional data.


page 1

page 2

page 3

page 4


Local Differential Privacy: a tutorial

In the past decade analysis of big data has proven to be extremely valua...

A normal approximation for joint frequency estimatation under Local Differential Privacy

In the recent years, Local Differential Privacy (LDP) has been one of th...

Task-aware Privacy Preservation for Multi-dimensional Data

Local differential privacy (LDP), a state-of-the-art technique for priva...

Improved Matrix Gaussian Mechanism for Differential Privacy

The wide deployment of machine learning in recent years gives rise to a ...

The Limits of Pan Privacy and Shuffle Privacy for Learning and Estimation

There has been a recent wave of interest in intermediate trust models fo...

DP2-Pub: Differentially Private High-Dimensional Data Publication with Invariant Post Randomization

A large amount of high-dimensional and heterogeneous data appear in prac...

Design of Algorithms under Policy-Aware Local Differential Privacy: Utility-Privacy Trade-offs

Local differential privacy (LDP) enables private data sharing and analyt...