Preprint · 2017 · Open access

PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training

Meng Li, Liangzhen Lai, Naveen Suda, Vikas Chandra, David Zhigang Pan

arXiv (Cornell University) · Published 18 September 2017 · DOI 10.48550/arxiv.1709.06161

Open PDFView at the publisherCite this paper

In brief

“PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training” is a 2017 preprint by Meng Li and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 39 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
39
Most cited in
2019 (9)
References
32
Authors
5

Abstract

Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services but suffer from potential privacy risks due to excessive user data collection. To enable cloud-based DNN training while protecting the data privacy simultaneously, we propose to leverage the intermediate representations of the data, which is achieved by splitting the DNNs and deploying them separately onto local platforms and the cloud. The local neural network (NN) is used to generate the feature representations. To avoid local training and protect data privacy, the local NN is derived from pre-trained NNs. The cloud NN is then trained based on the extracted intermediate representations for the target learning task. We validate the idea of DNN splitting by characterizing the dependency of privacy loss and classification accuracy on the local NN topology for a convolutional NN (CNN) based image classification task. Based on the characterization, we further propose PrivyNet to determine the local NN topology, which optimizes the accuracy of the target learning task under the constraints on privacy loss, local computation, and storage. The efficiency and effectiveness of PrivyNet are demonstrated with the CIFAR-10 dataset.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, M., Lai, L., Suda, N., Chandra, V., & Pan, D. Z. (2017). PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1709.06161

MLA 9

Li, Meng, et al. “PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training.” arXiv (Cornell University), 2017. https://doi.org/10.48550/arxiv.1709.06161.

Chicago

Li, Meng, Liangzhen Lai, Naveen Suda, Vikas Chandra, and David Zhigang Pan. 2017. “PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1709.06161.

Harvard

Li, M. et al. (2017) ‘PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training’, arXiv (Cornell University). doi:10.48550/arxiv.1709.06161.

IEEE

M. Li, L. Lai, N. Suda, V. Chandra, and D. Z. Pan, “PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training,” arXiv (Cornell University), 2017, doi: 10.48550/arxiv.1709.06161.

BibTeX

@misc{li2017privynet,
  title     = {{PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training}},
  author    = {Li, Meng and Lai, Liangzhen and Suda, Naveen and Chandra, Vikas and Pan, David Zhigang},
  howpublished = {arXiv (Cornell University)},
  year      = {2017},
  doi       = {10.48550/arxiv.1709.06161},
  url       = {https://doi.org/10.48550/arxiv.1709.06161}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201866
201999
202077
202122
202255
202355
202433
202511
202611

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • cloud-based training
  • intermediate representation
  • feature extraction
  • pre-trained neural networks
  • privacy-accuracy trade-off
  • convolutional neural networks
  • image classification
  • resource-constrained devices

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, M., Lai, L., Suda, N., Chandra, V., & Pan, D. Z. (2017). PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1709.06161

How many times has this paper been cited?

39 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Meng Li, Liangzhen Lai, Naveen Suda, Vikas Chandra, David Zhigang Pan.

What is the DOI of this paper?

10.48550/arxiv.1709.06161, permanently at https://doi.org/10.48550/arxiv.1709.06161. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.