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
Items 201–249 of 249
Differentially Private Tensor Deep Computation for Cyber–Physical–Social Systems
Gati, N. J., Yang, L. T., Feng, J., Zhang, S., & Ren, Z. (2020) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2020.3004148 · Cited by 2
Towards Proactive Context-Aware IoT Environments by Means of Federated Learning
Rentero-Trejo, R., Flores-Martin, D., Galán–Jiménez, J., García-Alonso, J. M., Murillo, J. M., & Berrocal, J. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-92231-3_3 · Cited by 2
Scaling Data Analysis Services in an Edge-based Federated Learning Environment
Catalfamo, A., Carnevale, L., Galletta, A., Martella, F., Celesti, A., Fazio, M. C., & Villari, M. (2022) · IEEE/ACM International Conference on Utility and Cloud Computing (UCC) · doi:10.1109/ucc56403.2022.00030 · Cited by 2
Communication Efficient and Differentially Private Logistic Regression under the Distributed Setting
Bao, E., Gao, D., Xiao, X., & Li, Y. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599279 · Cited by 5
A Survey on Data Distribution Challenges and Solutions in Vertical and Horizontal Federated Learning
Jahani, K., Moshiri, B., & Khalaj, B. H. (2024) · Journal of Artificial Intelligence Applications and Innovations · doi:10.61838/jaiai.1.2.5 · Cited by 4
Controlling the performance of deep neural networks using a single parameter
Luo, Y., Li, S., Zhang, X., & Feng, G. (2024) · Evolutionary Intelligence · doi:10.1007/s12065-024-00939-2 · Cited by 1
A bimodal lattice-based linearly homomorphic signature for chain-based implicit data storage scheme
Li, R., Zhou, T., Han, Y., Che, X., & Yang, X. (2025) · Discover Computing · doi:10.1007/s10791-025-09728-6 · Cited by 1
Privacy‐Preserving Hierarchical Federated Learning With Front‐Loaded Differential Privacy Mechanism
Ratnayake, H., Chen, L., & Ding, X. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70411 · Cited by 3
FEDERATED LEARNING ON STOCHASTIC NEURAL NETWORKS
Tang, J., Bausback, R., Bao, F., & Archibald, R. K. (2025) · Journal of Machine Learning for Modeling and Computing · doi:10.1615/jmachlearnmodelcomput.2025060047 · Cited by 1
Using Anonymous Protocol for Privacy Preserving Deep Learning Model
Tran, A. T., Luong, T. D., Dang, V. H., & Huynh, V. (2020) · NAFOSTED Conference on Information and Computer Science (NICS) · doi:10.1109/nics51282.2020.9335880 · Cited by 1
A Secure Word Vector Training Scheme Based on Inner-Product Functional Encryption
Zhang, M., Li, Z.-A., & Zhang, P. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7242-3_5 · Cited by 1
Data analysis with performance and privacy enhanced classification
Tajanpure, R., & Muddana, A. L. (2023) · Journal of Intelligent Systems · doi:10.1515/jisys-2022-0215 · Cited by 3
Privacy-Preserving Cloud-Edge Collaborative K-Means Clustering Model in IoT
Wang, C., Xu, J. F., Tan, S., & Yin, L. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9331-4_44 · Cited by 2
SEAFL: Transforming Federated Learning for Enhanced Privacy in 6G-Enabled Vehicles
Vinita, L. J., & Vetriselvi, V. (2023) · Annual International Conference on Emerging Research Areas and International Conference on Microelectronics, Communications and Renewable Energy · doi:10.1109/aicera/icis59538.2023.10420354 · Cited by 2
A conceptual approach of optimization in federated learning
Mar’i, F., & Supianto, A. A. (2024) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v37.i1.pp288-299 · Cited by 1
HybridFL: Hybrid Approach Toward Privacy-Preserving Federated Learning
Ali, S., Mamoon, S., Usman, A., Abidin, Z. U., & Zhao, C. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-73699-5_1 · Cited by 2
FedQP: Large-Scale Private and Flexible Federated Query Processing
Almohri, H. M. J., & Watson, L. T. (2025) · IEEE Access · doi:10.1109/access.2025.3567487 · Cited by 1
Towards Undistillable Models by Minimizing Conditional Mutual InformationPreprint
Ye, L., Hamidi, S. M., & Yang, E.-H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.00012 · Cited by 1
DP-MAC: The Differentially Private Method of Auxiliary Coordinates for Deep LearningPreprint
Harder, F., Köhler, J., Welling, M., & Park, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.06924
Machine Learning Techniques for Homomorphically Encrypted Data
Kumbhar, H. R., & Rao, S. S. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-4029-5_25
A Fine-tuning-based Adversarial Network for Member Privacy Preserving
Lu, X., Ren, Q., & Tian, F. (2021) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana53684.2021.00082
Privacy-Preserving and Auditable Federated Deep Reinforcement Learning for Robotic Manipulation
Zhu, X., & Li, H. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-92708-0_20
IOT Based Privacy Preserving Machine Learning Algorithm for High-Speed Encryption
Aggarwal, A., & Arora, S. (2022) · Advances in transdisciplinary engineering · doi:10.3233/atde220751
A Review on Machine Learning Techniques on IOT Based Privacy Preserving Network
Aggarwal, A., & Arora, S. (2022) · Advances in transdisciplinary engineering · doi:10.3233/atde220798
Privacy Preserving Systems Adoptable in Cloud Image Retrieval
Gayathri, S., & Gowri, S. (2022) · International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) · doi:10.1109/icaiss55157.2022.10010857
A Hardware Security Isolation Architecture for Intelligent Accelerator
Gong, R. K., Wang, L., Shi, W., Liu, W., & Zhang, J. (2022) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom56396.2022.00135
Xu, L. (2024) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp62122.2024.10743579
Comparative Study of Pre-Trained CNN for Pinkeye Disease Detection in Cattle and Goat Eyes
Faurina, R., Rahman, M., & Agustian, I. (2025) · Engineering headway · doi:10.4028/p-j2a9ou
Q-DeepCuckoo: A Quantum-Assisted Federated Framework for Dynamic CH Optimization in 6G-IoT NetworksPreprint
Kadumbadi, V., & Thirumaraiselvan, P. (2025) · doi:10.1364/opticaopen.30405124.v1 · Cited by 1
Q-DeepCuckoo: A Quantum-Assisted Federated Framework for Dynamic CH Optimization in 6G-IoT NetworksPreprint
Thirumaraiselvan, P., & Kadumbadi, V. (2025) · doi:10.1364/opticaopen.30405124.v2
Q-DeepCuckoo: A Quantum-Assisted Federated Framework for Dynamic CH Optimization in 6G-IoT NetworksPreprint
Thirumaraiselvan, P., & Kadumbadi, V. (2025) · doi:10.1364/opticaopen.30405124.v3
ConvXformer: Differentially Private Hybrid ConvNeXt-Transformer for Inertial Navigation
Tariq, O., Bilal, M., Hassan, M. U., Han, D., & Crowcroft, J. (2026) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2026.3702897
Morovich, E. (2025) · International Journal for Research Publication and Seminars · doi:10.36676/jrps.v16.i4.334
Dalvi, A. B. (2023) · TRAP@NCI (National College of Ireland)
Privacy and Robustness in Federated Learning: From Theoretical Insights to Practical Implementation
Stephan, J. (2025) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.5075/epfl-thesis-10503
On-demand Crowdsourced Federated Learning over Edge Devices
Tahir, M. (2025) · Dublin City University Open Access Institutional Repository (Dublin City University)
Boulemtafes, A., Derhab, A., & Challal, Y. (2025) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa66935.2025.11315416
Dynamic Trust-Driven Blockchain Federated Learning System for Medical Insurance Fraud Detection
Jeevarathinam, M., & G.Kumaravelan (2026) · International Conference on AI-Driven Smart Systems and Ubiquitous Computing (ICAUC) · doi:10.1109/icauc68182.2026.11441105
Truong, X. H., Luong, T. D., Tran, A. T., & Vo, M. N. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-21631-1_9
Architectures réparties et conteneurs logiciels sécurisés pour coopérations médicales multi-sites
Sayadi, S. (2022) · theses.fr (ABES) · doi:10.70675/17bc7dd7z206fz44b9z976bz45049c4b5a2a
Plassier, V. (2023) · theses.fr (ABES) · doi:10.70675/9b6101b0zc3dez4c4az9bb1zc3b4392f012a
Leakage of Sensitive Data from Deep Neural Networks
Grosso, G. D. (2023) · theses.fr (ABES) · doi:10.70675/4750e977z8d15z41fez8542z9899c2e11952 · Cited by 1
Adaptive and efficient continual learning in dynamic environments
Yang, R. (2025) · theses.fr (ABES) · doi:10.70675/77589246z70dfz4da8za0f0z645d1e2fa13e
Model Training for Edge Video Analytics
Bai, T. (2025) · Textbooks in telecommunication engineering · doi:10.1007/978-3-032-14764-6_4
Adaptive Prompt Evolution for Continual Learning in Diabetic Retinopathy Detection
Bravo-Rocca, G., Liu, P., Guitart, J., Dholakia, A., Ellison, D. D., & Carrillo-Larco, R. M. (2026) · SN Computer Science · doi:10.1007/s42979-026-05036-y
BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain UnderstandingPreprint
Nguyen, X.-B., Truong, T.-D., Sinha, P., & Luu, K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6814918 · Cited by 1
Privacy in Federated Learning Models for Intrusion Detection Systems
Schneider, E., Bezawada, B., & Ray, I. (2026) · Digital Threats Research and Practice · doi:10.1145/3828661
Vutukuri, Y. K. R., Gudibandla, R. S., Goruputi, D. S., Kottapalli, V., Pradhan, N. R., & Varri, U. S. (2026) · IEEE Access · doi:10.1109/access.2026.3727028
Govindaraj, V., Krishnammal, P. M., Devi, S. S., Nettem, A. V., Vinoth Kumar, V., & Yizengaw, A. W. (2026) · Discover Computing · doi:10.1007/s10791-026-10502-5 · Cited by 1
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
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.