Preserving differential privacy in convolutional deep belief networks

Nhat Hai Phan, Xintao Wu, Dejing Dou

Research output: Contribution to journalArticlepeer-review

60 Scopus citations


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.

Original languageEnglish (US)
Pages (from-to)1681-1704
Number of pages24
JournalMachine Learning
Issue number9-10
StatePublished - Oct 1 2017

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence


  • Deep learning
  • Differential privacy
  • Health informatics
  • Human behavior prediction
  • Image classification


Dive into the research topics of 'Preserving differential privacy in convolutional deep belief networks'. Together they form a unique fingerprint.

Cite this