Preprint · 2019 · Open access

Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge.

Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Dean Michael Tullsen, Hadi Esmaeilzadeh

arXiv (Cornell University) · Published 26 May 2019

Open full textCite this paper

In brief

“Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge.” is a 2019 preprint by Fatemehsadat Mireshghallah and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 7 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
7
Most cited in
2022 (2)
Authors
5

Abstract

A wide variety of DNN applications increasingly rely on the cloud to perform their huge computation. This heavy trend toward cloud-hosted inference services raises serious privacy concerns. This model requires the sending of private and privileged data over the network to remote servers, exposing it to the service provider. Even if the provider is trusted, the data can still be vulnerable over communication channels or via side-channel attacks [1,2] at the provider. To that end, this paper aims to reduce the information content of the communicated data without compromising the cloud service's ability to provide a DNN inference with acceptably high accuracy. This paper presents an end-to-end framework, called Shredder, that, without altering the topology or the weights of a pre-trained network, learns an additive noise distribution that significantly reduces the information content of communicated data while maintaining the inference accuracy. Shredder learns the additive noise by casting it as a tensor of trainable parameters enabling us to devise a loss functions that strikes a balance between accuracy and information degradation. The loss function exposes a knob for a disciplined and controlled asymmetric trade-off between privacy and accuracy. While keeping the DNN intact, Shredder enables inference on noisy data without the need to update the model or the cloud. Experimentation with real-world DNNs shows that Shredder reduces the mutual information between the input and the communicated data to the cloud by 70.2% compared to the original execution while only sacrificing 1.46% loss in accuracy.

Cite this paper

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

APA 7

Mireshghallah, F., Taram, M., Ramrakhyani, P., Tullsen, D. M., & Esmaeilzadeh, H. (2019). Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge. arXiv (Cornell University). https://arxiv.org/pdf/1905.11814.pdf

MLA 9

Mireshghallah, Fatemehsadat, et al. “Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge.” arXiv (Cornell University), 2019. https://arxiv.org/pdf/1905.11814.pdf.

Chicago

Mireshghallah, Fatemehsadat, Mohammadkazem Taram, Prakash Ramrakhyani, Dean Michael Tullsen, and Hadi Esmaeilzadeh. 2019. “Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge.” arXiv (Cornell University). https://arxiv.org/pdf/1905.11814.pdf.

Harvard

Mireshghallah, F. et al. (2019) ‘Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge.’, arXiv (Cornell University). Available at: https://arxiv.org/pdf/1905.11814.pdf.

IEEE

F. Mireshghallah, M. Taram, P. Ramrakhyani, D. M. Tullsen, and H. Esmaeilzadeh, “Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge.,” arXiv (Cornell University), 2019.

BibTeX

@misc{mireshghallah2019shredder,
  title     = {{Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge.}},
  author    = {Mireshghallah, Fatemehsadat and Taram, Mohammadkazem and Ramrakhyani, Prakash and Tullsen, Dean Michael and Esmaeilzadeh, Hadi},
  howpublished = {arXiv (Cornell University)},
  year      = {2019},
  url       = {https://arxiv.org/pdf/1905.11814.pdf}
}

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

Citations by year

YearCitationsShare of the best year
202111
202222
202311
202411
202522

Topic and keywords

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

  • edge inference
  • cloud inference
  • privacy-accuracy trade-off
  • side-channel attacks
  • information leakage
  • loss function design

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?

Mireshghallah, F., Taram, M., Ramrakhyani, P., Tullsen, D. M., & Esmaeilzadeh, H. (2019). Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge. arXiv (Cornell University). https://arxiv.org/pdf/1905.11814.pdf

How many times has this paper been cited?

7 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 full text from this page.

Who wrote this paper?

Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Dean Michael Tullsen, Hadi Esmaeilzadeh.

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.