Preserving differential privacy in convolutional deep belief networks

69Citations
Citations of this article
161Readers
Mendeley users who have this article in their library.

Abstract

The remarkable development of deep learning in medicine and healthcare domain presents obvious privacy issues, when deep neural networks are built on users’ personal and highly sensitive data, e.g., clinical records, user profiles, biomedical images, etc. However, only a few scientific studies on preserving privacy in deep learning have been conducted. In this paper, we focus on developing a private convolutional deep belief network (pCDBN), which essentially is a convolutional deep belief network (CDBN) under differential privacy. Our main idea of enforcing ϵ-differential privacy is to leverage the functional mechanism to perturb the energy-based objective functions of traditional CDBNs, rather than their results. One key contribution of this work is that we propose the use of Chebyshev expansion to derive the approximate polynomial representation of objective functions. Our theoretical analysis shows that we can further derive the sensitivity and error bounds of the approximate polynomial representation. As a result, preserving differential privacy in CDBNs is feasible. We applied our model in a health social network, i.e., YesiWell data, and in a handwriting digit dataset, i.e., MNIST data, for human behavior prediction, human behavior classification, and handwriting digit recognition tasks. Theoretical analysis and rigorous experimental evaluations show that the pCDBN is highly effective. It significantly outperforms existing solutions.

References Powered by Scopus

76931Citations
26295Readers
Get full text
63550Citations
45356Readers
Get full text
44103Citations
19050Readers
Get full text

Cited by Powered by Scopus

Federated Learning

526Citations
544Readers
Get full text
181Citations
190Readers

GANobfuscator: Mitigating information leakage under GAN via differential privacy

173Citations
133Readers
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Phan, N. H., Wu, X., & Dou, D. (2017). Preserving differential privacy in convolutional deep belief networks. Machine Learning, 106(9–10), 1681–1704. https://doi.org/10.1007/s10994-017-5656-2

Readers over time

‘17‘18‘19‘20‘21‘22‘23‘24‘25010203040

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 61

66%

Researcher 15

16%

Lecturer / Post doc 10

11%

Professor / Associate Prof. 6

7%

Readers' Discipline

Tooltip

Computer Science 81

80%

Engineering 9

9%

Social Sciences 7

7%

Mathematics 4

4%

Save time finding and organizing research with Mendeley

Sign up for free
0