Journal
MACHINE LEARNING
Volume 106, Issue 9-10, Pages 1681-1704Publisher
SPRINGER
DOI: 10.1007/s10994-017-5656-2
Keywords
Deep learning; Differential privacy; Human behavior prediction; Health informatics; Image classification
Categories
Funding
- NIH [R01GM103309]
- NSF [1502273, 1523115, 1118050]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1502273] Funding Source: National Science Foundation
- Direct For Education and Human Resources
- Division Of Graduate Education [1523154, 1523115] Funding Source: National Science Foundation
- Div Of Information & Intelligent Systems
- Direct For Computer & Info Scie & Enginr [1118050, 1502172] Funding Source: National Science Foundation
Ask authors/readers for more resources
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 -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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available