Smith, M.T., Zwiessele, M. and Lawrence, N.D. (Submitted: 2017) Differentially Private Gaussian Processes. arXiv. (Unpublished)
Abstract
A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the Differential Privacy framework with the flexibility of Gaussian processes (GPs). We propose a method using GPs to provide Differentially Private (DP) regression. We then improve this method by crafting the DP noise covariance structure to efficiently protect the training data, while minimising the scale of the added noise. We find that, for the dataset used, this cloaking method achieves the greatest accuracy, while still providing privacy guarantees, and offers practical DP for regression over multi-dimensional inputs. Together these methods provide a starter toolkit for combining differential privacy and GPs.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2017 The Author(s). |
Keywords: | stat.ML; stat.ML; cs.LG; 60G15; G.3 |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number EUROPEAN COMMISSION - FP6/FP7 MLPM2012 - 316861 ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL (EPSRC) EP/N014162/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 20 Jun 2017 08:37 |
Last Modified: | 20 Jun 2017 08:37 |
Published Version: | https://arxiv.org/abs/1606.00720 |
Status: | Unpublished |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:117494 |