UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Differentially Private Mixture of Generative Neural Networks

Acs, G; Melis, L; Castelluccia, C; De Cristofaro, E; (2017) Differentially Private Mixture of Generative Neural Networks. In: Raghavan, V and Aluru, S and Karypis, G and Miele, L and Wu, X, (eds.) Proceedings of the 17th International Workshop on Digital Mammography: 10th International Workshop, IWDM 2010, Girona, Catalonia, Spain, June 16-18, 2010. (pp. pp. 715-720). IEEE: Louisiana, USA. Green open access

[img]
Preview
Text
1709.04514v1.pdf - ["content_typename_Accepted version" not defined]

Download (870kB) | Preview

Abstract

Generative models are used in an increasing number of applications that rely on large amounts of contextually rich information about individuals. Owing to possible privacy violations, however, publishing or sharing generative models is not always viable. In this paper, we introduce a novel solution for privately releasing generative models and entire high-dimensional datasets produced by these models. We model the generator distribution of the training data by a mixture of k generative neural networks. These are trained together and collectively learn the generator distribution of a dataset. Data is divided into k clusters, using a novel differentially private kernel k-means, then each cluster is given to separate generative neural networks, such as Restricted Boltzmann Machines or Variational Autoencoders, which are trained only on their own cluster using differentially private gradient descent. We evaluate our approach using the MNIST dataset and a large Call Detail Records dataset, showing that it produces realistic synthetic samples, which can also be used to accurately compute arbitrary number of counting queries.

Type: Proceedings paper
Title: Differentially Private Mixture of Generative Neural Networks
Event: 17th IEEE International Conference on Data Mining (ICDMW), 18-21 November 2017
Location: New Orleans, LA
Dates: 18 November 2017 - 21 November 2017
ISBN-13: 978-1-5386-3835-4
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICDM.2017.81
Publisher version: http://dx.doi.org/10.1109/ICDM.2017.81
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Data models, Kernel, Data privacy, Privacy, Neural networks, Training, Standards
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: http://discovery.ucl.ac.uk/id/eprint/1574604
Downloads since deposit
46Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item