Privacy-preserving deep learning
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Deep learning based on artificial neural networks is a very popular approach to modeling, classifying, and recognizing complex data such as images, speech, and text. The unprecedented accuracy of deep learning methods has turned them into the foundation of new AI-based services on the Internet. Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training. Massive data collection required for deep learning presents obvious privacy issues. Users' personal, highly sensitive data such as photos and voice recordings is kept indefinitely by the companies that collect it. Users can neither delete it, nor restrict the purposes for which it is used. Furthermore, centrally kept data is subject to legal subpoenas and extrajudicial surveillance. Many data owners-for example, medical institutions that may want to apply deep learning methods to clinical records-are prevented by privacy and confidentiality concerns from sharing the data and thus benefitting from large-scale deep learning. In this paper, we present a practical system that enables multiple parties to jointly learn an accurate neural-network model for a given objective without sharing their input datasets. We exploit the fact that the optimization algorithms used in modern deep learning, namely, those based on stochastic gradient descent, can be parallelized and executed asynchronously. Our system lets participants train independently on their own datasets and selectively share small subsets of their models' key parameters during training. This offers an attractive point in the utility/privacy tradeoff space: participants preserve the privacy of their respective data while still benefitting from other participants' models and thus boosting their learning accuracy beyond what is achievable solely on their own inputs. We demonstrate the accuracy of our privacy-preserving deep learning on benchmark datasets.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Federated AI addresses some of these aspects19,25. Data are kept locally and local confidentiality issues are addressed26, but model parameters are still handled by central custodians, which concentrates power. Furthermore, such star-shaped architectures decrease fault tolerance.”
From Swarm Learning for decentralized and confidential clinical machine learning (2021) · cites this paper as [26]
In the citing paper
“we showed that models can reach a comparable performance even when only 25% of the weight updates are shared”
From Federated learning for predicting clinical outcomes in patients with COVID-19 (2021) · cites this paper as [51]
In the citing paper
“These backdoor detection algorithms can however be bypassed by maximizing the latent indistinguishability of backdoor-enabled adversarial inputs and clean inputs [154].”
From Privacy and Robustness in Federated Learning: Attacks and Defenses (2024) · cites this paper as [154]
Citations
Cites
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356
Self-citation
Cited by
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455
Zhang, Y., Xiang, T., Hospedales, T. M., & Lu, H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00454 · Cited by 1,752
Swarm Learning for decentralized and confidential clinical machine learning
Warnat-Herresthal, S., Schultze, H., Shastry, K. L., Manamohan, S., Mukherjee, S., Garg, V., Sarveswara, R., Händler, K., Pickkers, P., Aziz, N. A., et al. (2021) · Nature · doi:10.1038/s41586-021-03583-3 · Cited by 884
Federated learning for predicting clinical outcomes in patients with COVID-19
Dayan, I., Roth, H. R., Zhong, A., Harouni, A., Gentili, A., Abidin, A. Z., Liu, A., Costa, A. B., Wood, B. J., Tsai, C.-S., et al. (2021) · Nature Medicine · doi:10.1038/s41591-021-01506-3 · Cited by 842
DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-based Incentive
Weng, J., Weng, J., Zhang, J., Li, M., Zhang, Y., & Luo, W. (2019) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2019.2952332 · Cited by 610
Metadata
- Authors
- Shokri, R., & Shmatikov, V.
- Affiliations
- The University of Texas at Austin (US)
- Cornell Tech (US)
- Venue
- 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)
- Publisher
- IEEE
- Published
- 2015-09
- Pages
- 909-910
- OpenAlex
- W2337093093
- Cited by
- 223
- References
- 1
- Citations by year
- 2026: 9 · 2025: 27 · 2024: 23 · 2023: 44 · 2022: 34 · 2021: 42 · 2020: 18 · 2019: 13 · 2018: 10 · 2017: 2 · 2016: 1
- FWCI
- 2.44
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Allerton Conference on Communication, Control, and Computing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Keywords
- privacy-preserving deep learning, federated learning, parameter sharing, stochastic gradient descent, data privacy, privacy-utility trade-off
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Privacy-preserving deep learning. https://app.cochat.ai/papers/10.1109/allerton.2015.7447103
- The paper
- Shokri, R., & Shmatikov, V. (2015). Privacy-preserving deep learning. 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton). https://doi.org/10.1109/allerton.2015.7447103
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.