Conference paper · 2020 · Open access
Shredder: Learning Noise Distributions to Protect Inference Privacy
International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 3–18 · Published 9 March 2020 · DOI 10.1145/3373376.3378522
In brief
“Shredder: Learning Noise Distributions to Protect Inference Privacy” is a 2020 conference paper by Fatemehsadat Mireshghallah and 5 co-authors, published in International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). OpenAlex counts 133 citations as of 19 November 2026, which puts it in the top 7% of works published in 2020 by citations. It is open access: the full text is free to read at International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS).
- Citations
- 133
- Most cited in
- 2024 (23)
- Field-weighted impact
- 4.30
- References
- 81
- Authors
- 6
Abstract
A wide variety of deep neural applications increasingly rely on the cloud to perform their compute-heavy inference. This common practice requires sending private and privileged data over the network to remote servers, exposing it to the service provider and potentially compromising its privacy. Even if the provider is trusted, the data can still be vulnerable over communication channels or via side-channel attacks in the cloud. To that end, this paper aims to reduce the information content of the communicated data with as little as possible compromise on the inference accuracy by making the sent data noisy. An undisciplined addition of noise can significantly reduce the accuracy of inference, rendering the service unusable. To address this challenge, this paper devises Shredder, an end-to-end framework, that, without altering the topology or the weights of a pre-trained network, learns additive noise distributions that significantly reduce the information content of communicated data while maintaining the inference accuracy. The key idea is finding the additive noise distributions by casting it as a disjoint offline learning process with a loss function that strikes a balance between accuracy and information degradation. The loss function also exposes a knob for a disciplined and controlled asymmetric trade-off between privacy and accuracy. While keeping the DNN intact, Shredder divides inference between the cloud and the edge device, striking a balance between computation and communication. In the separate phase of inference, the edge device takes samples from the Laplace distributions that were collected during the proposed offline learning phase and populates a noise tensor with these sampled elements. Then, the edge device merely adds this populated noise tensor to the intermediate results to be sent to the cloud. As such, Shredder enables accurate inference on noisy intermediate data without the need to update the model or the cloud, or any training process during inference. We also formally show that Shredder maximizes privacy with minimal impact on DNN accuracy while the tradeoff between privacy and accuracy is controlled through a mathematical knob. Experimentation with six real-world DNNs from text processing and image classification shows that Shredder reduces the mutual information between the input and the communicated data to the cloud by 74.70% compared to the original execution while only sacrificing 1.58% loss in accuracy. On average, Shredder also offers a speedup of 1.79x over Wi-Fi and 2.17x over LTE compared to cloud-only execution when using an off-the-shelf mobile GPU (Tegra X2) on the edge.
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., Jalali, A., Tullsen, D. M., & Esmaeilzadeh, H. (2020). Shredder: Learning Noise Distributions to Protect Inference Privacy. International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 3–18. https://doi.org/10.1145/3373376.3378522
MLA 9
Mireshghallah, Fatemehsadat, et al. “Shredder: Learning Noise Distributions to Protect Inference Privacy.” International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2020, pp. 3–18. https://doi.org/10.1145/3373376.3378522.
Chicago
Mireshghallah, Fatemehsadat, Mohammadkazem Taram, Prakash Ramrakhyani, Ali Jalali, Dean Michael Tullsen, and Hadi Esmaeilzadeh. 2020. “Shredder: Learning Noise Distributions to Protect Inference Privacy.” International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS): 3–18. https://doi.org/10.1145/3373376.3378522.
Harvard
Mireshghallah, F. et al. (2020) ‘Shredder: Learning Noise Distributions to Protect Inference Privacy’, International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), pp. 3–18. doi:10.1145/3373376.3378522.
IEEE
F. Mireshghallah, M. Taram, P. Ramrakhyani, A. Jalali, D. M. Tullsen, and H. Esmaeilzadeh, “Shredder: Learning Noise Distributions to Protect Inference Privacy,” International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), pp. 3–18, 2020, doi: 10.1145/3373376.3378522.
BibTeX
@inproceedings{mireshghallah2020shredder,
title = {{Shredder: Learning Noise Distributions to Protect Inference Privacy}},
author = {Mireshghallah, Fatemehsadat and Taram, Mohammadkazem and Ramrakhyani, Prakash and Jalali, Ali and Tullsen, Dean Michael and Esmaeilzadeh, Hadi},
booktitle = {International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
year = {2020},
pages = {3--18},
doi = {10.1145/3373376.3378522},
url = {https://doi.org/10.1145/3373376.3378522}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2018 | 1 | |
| 2019 | 2 | |
| 2020 | 8 | |
| 2021 | 20 | |
| 2022 | 15 | |
| 2023 | 21 | |
| 2024 | 23 | |
| 2025 | 22 | |
| 2026 | 21 |
Its field-weighted citation impact is 4.30: it has been cited 4.30 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- inference privacy
- cloud inference
- noise injection
- Laplace distribution
- privacy-accuracy trade-off
- side-channel attacks
- communication privacy
- offline learning
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Mireshghallah, F., Taram, M., Ramrakhyani, P., Jalali, A., Tullsen, D. M., & Esmaeilzadeh, H. (2020). Shredder: Learning Noise Distributions to Protect Inference Privacy. International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 3–18. https://doi.org/10.1145/3373376.3378522
How many times has this paper been cited?
133 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 International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS): sign in and open the PDF from this page.
Who wrote this paper?
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Ali Jalali, Dean Michael Tullsen, Hadi Esmaeilzadeh.
What is the DOI of this paper?
10.1145/3373376.3378522, permanently at https://doi.org/10.1145/3373376.3378522. 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.