Privacy-Preserving Deep Learning
The DOI matches its Crossref record; 65 of the 67 references it cites were found in a registry or an index, and 2 are not checked yet.
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 extra-judicial 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.
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
“However, it has been shown that the models themselves can, under certain conditions, memorise information40–43.”
From The future of digital health with federated learning (2020) · cites this paper as [45]
In the citing paper
“A flaw of [46] is that it does not consider unbalanced and nonindependent identical distribution (non-IID) data.”
From Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019) · cites this paper as [46]
In the citing paper
“Specifically, while preserving client's own privacy, the training loss can be reduced by sharing the models among clients, comparing to training solely on their own inputs.”
From Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019) · cites this paper as [46]
In the citing paper
“In decentralized learning systems, such as distributed selective stochastic gradient descent [35] and federated learning (FL) [36], data are trained locally by different participants without data sharing.”
From Generative AI in medical practice: in-depth exploration of privacy and security challenges (2024) · cites this paper as [35]
In the citing paper
“This setup can protect data privacy to some extent, but it is not perfect.”
From Generative AI in medical practice: in-depth exploration of privacy and security challenges (2024) · cites this paper as [35]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“Deep learning has been shown to outperform traditional techniques for speech recognition [23,24,27], image recognition [30,45], and face detection [48].”
BackgroundGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 2×
“The first is the MNIST dataset [31] of handwritten digits formatted as 32x32 images, normalized so that the digits are located at the center of the image.”
Background(2014) · Cited by 33,419
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 2×
“The unprecedented accuracy of the resulting models allows them to be used as the foundation of many new services and applications, including accurate speech recognition [24] and image recognition that outperforms humans [26].”
BackgroundHinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · cited 1×
“Deep learning has been shown to outperform traditional techniques for speech recognition [23,24,27], image recognition [30,45], and face detection [48].”
BackgroundLearning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239 · cited 1×
“Surveys of deep-learning architectures, algorithms, and applications can be found in [5, 16].”
Background(2012) · Cited by 9,062
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“Deep learning has been shown to outperform traditional techniques for speech recognition [23,24,27], image recognition [30,45], and face detection [48].”
Background(2010) · Cited by 8,261
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · cited 1×
“This is also consistent with regularizing techniques that randomly corrupt neurons [47] or input data [52] during training in order to avoid overfitting.”
Background
Research works printed but not linked: 17
- Chaudhuri K., 2009, NIPS
- Collobert R., 2011, NIPS Workshop
- Dean J., 2012, NIPS
- Denas O., 2013, ICML Workshop
- Fakoor R., 2013, WHEALTH
- Krizhevsky A., 2012, NIPS
- 10.5555/646765.704129 · doi:10.5555/646765.704129
- Netzer Y., 2011, NIPS Workshop
- Pathak M., 2010, NIPS
- Recht B., 2011, NIPS
- Roy I., 2010, NSDI
- 10.5555/65669.104449 · doi:10.5555/65669.104449
- Shultz D., 2015, Science, 347(6221)
- Simard P., 2013, Document Analysis and Recognition
- Wainwright M., 2012, NIPS
- Wolinsky D., 2012, OSDI
- Zinkevich M., 2010, NIPS
Cited by
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
“Perhaps the most relevant prior work is that of Shokri & Shmatikov (2015).”
BackgroundDeep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578
“[52] R. Shokri and V. Shmatikov.”
BackgroundMethodInfluentialFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
“Ref [47] approached the problem with Stochastic Gradient Descent (SGD) and they also proposed privacy-preserving protocols for logistic regression and neural networks.”
BackgroundInfluentialMembership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754
“Differential privacy [12] has been applied to linear and logistic regression [8], [37], support vector machines [28], risk minimization [5], [9], [34], deep learning [1], [30], learning an unknown probability distribution over a discrete population from random samples [10], and releasing hyper-parameters and classifie…”
BackgroundSelf-citationThe future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015
“Therefore the FL setup can be further enhanced by privacy protections using mechanisms such as differential privacy [34, 35] or learning from encrypted data (c.”
Method
Metadata
- Authors
- Shokri, R., & Shmatikov, V.
- Affiliations
- The University of Texas at Austin (US)
- Cornell University (US)
- Venue
- Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2015-10-12
- Pages
- 1310-1321
- ISSN
- 1543-7221 (ISSN-L)
- OpenAlex
- W2053637704
- Cited by
- 2,356
- References
- 66
- Citations by year
- 2026: 141 · 2025: 282 · 2024: 267 · 2023: 267 · 2022: 252 · 2021: 334 · 2020: 373 · 2019: 227 · 2018: 122 · 2017: 68 · 2016: 20 · 2015: 2
- FWCI
- 39.81
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGSAC Conference on Computer and Communications Security (CCS) (publishedVersion)
- National University of Singapore (submittedVersion)
- Funders
- National Institutes of Health (LM011028-01)
- National Science Foundation (1223396 and 1408944)
- Schweizerische Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- 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, data privacy, artificial neural networks, user data collection, sensitive personal data, data sharing, medical data confidentiality, surveillance, data protection
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/10.1145/2810103.2813687
- The paper
- Shokri, R., & Shmatikov, V. (2015). Privacy-Preserving Deep Learning. Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security. https://doi.org/10.1145/2810103.2813687
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.