The DOI matches its Crossref record, with a small difference in title or year; 101 of the 107 references it cites were found in a registry or an index, and 1 are not checked yet.
A Survey on Differentially Private Machine Learning [Review Article]
Abstract
Recent years have witnessed remarkable successes of machine learning in various applications. However, machine learning models suffer from a potential risk of leaking private information contained in training data, which have attracted increasing research attention. As one of the mainstream privacy- preserving techniques, differential privacy provides a promising way to prevent the leaking of individual-level privacy in training data while preserving the quality of training data for model building. This work provides a comprehensive survey on the existing works that incorporate differential privacy with machine learning, so- called differentially private machine learning and categorizes them into two broad categories as per different differential privacy mechanisms: the Laplace/ Gaussian/exponential mechanism and the output/objective perturbation mechanism. In the former, a calibrated amount of noise is added to the non-private model and in the latter, the output or the objective function is perturbed by random noise. Particularly, the survey covers the techniques of differentially private deep learning to alleviate the recent concerns about the privacy of big data contributors. In addition, the research challenges in terms of model utility, privacy level and applications are discussed. To tackle these challenges, several potential future research directions for differentially private machine learning are pointed out.
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
“Differentially private (DP) deep learning (using a privatized gradient descent optimizer [1]) has been adopted to protect users and avoid legal risks of sensitive data use [27, 29].”
From Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings (2024) · cites this paper as [29]
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 20,507
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
DeepWalk: online learning of social representations
Perozzi, B., Al-Rfou, R., & Skiena, S. (2014) · Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2623330.2623732 · Cited by 10,123
k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
SWEENEY, L. (2002) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488502001648 · Cited by 8,571
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 7,330
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Deep 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
Flagged first, then by citations
5 of the 107 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Items 101–115 of 115
A Study of Multimodal Sentiment Analysis and Design of an Architecture
Vijayachandran, V., & Suchithra, R. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-3242-5_43
An Application Evaluation for Differentially Private Database Release Methods
Nicho, M., Walia, M., & Khan, S. N. (2024) · International Conference on Cryptography, Security and Privacy (CSP) · doi:10.1109/csp62567.2024.00013
A Weighted Privacy Mechanism under Differential Privacy
Hemkumar, D., & Prashanth, P. (2024) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit61985.2024.10626770
Securing Multi-Source Domain Adaptation With Global and Domain-Wise Privacy Demands
Chai, S., Xiao, Y., Liu, F., Zhu, J. L., & Zhou, Y. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3459890
Public Datasets: A Foundation to Artificial Intelligence in Health Care
Ferguson, S., & Tille, P. M. (2024) · American Society for Clinical Laboratory Science · doi:10.29074/ascls.2024003254
Calibrating Practical Privacy Risks for Differentially Private Machine Learning
Gu, Y., & Chen, K. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825354
Towards Assessing Integrated Differential Privacy and Fairness Mechanisms in Supervised Learning
Aldairi, M., & Joshi, J. B. D. (2024) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa62245.2024.00034
DPBRW-GGAN: Graph data generation based on biased random walk with differential privacy
Zhang, B., Liu, H., Tian, Y., et al. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114693
Efficient and privacy-preserving compressive learning
Chatalic, A. (2020) · theses.fr (ABES) · doi:10.70675/32098958z1deez4f21zb51az429b616621fd · Cited by 2
Sun, X., Xue, H., Sharma, D. P., Xue, L., Lin, X., & Xiong, P. (2026) · Journal of Information and Intelligence · doi:10.1016/j.jiixd.2026.05.005
Njungle, N. B., Jahns, E., Stojkov, M., & Kinsy, M. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-32575-4_7
Federated Learning in the Presence of Non-IID Data: A Systematic Survey
Barman, B., & Sarmah, S. (2026) · IEEE Guwahati Subsection Conference (GCON) · doi:10.1109/gcon69192.2026.11648411
Banerjee, S., Kumar, A., & Giri, V. K. (2026) · Iranian Journal of Science and Technology Transactions of Electrical Engineering · doi:10.1007/s40998-026-01226-9
Ensembling personalized quantum models with local differential privacy
Xhelollari, F., Chen, S. Y.-C., Farooq, J., & Chen, J. (2026) · Quantum Machine Intelligence · doi:10.1007/s42484-026-00440-2
Metadata
- Authors
- Gong, M., Xie, Y., Pan, K., Feng, K., & Qin, A. K.
- Affiliations
- Xidian University (CN)
- Swinburne University of Technology (AU)
- Venue
- IEEE Computational Intelligence Magazine
- Published
- 2020-05
- Volume
- 15
- Issue
- 2
- Pages
- 49-64
- ISSN
- 1556-603X (ISSN-L)
- 1556-6048
- OpenAlex
- W3016000170
- Semantic Scholar
- 0e9c4e5761d97bf538692c11cd267ad7affe708f
- Cited by
- 115
- References
- 107
- Citations by year
- 2026: 6 · 2025: 12 · 2024: 28 · 2023: 27 · 2022: 15 · 2021: 23 · 2020: 4
- FWCI
- 6.78
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Computational Intelligence Magazine (publishedVersion)
- Swinburne figshare (Swinburne University of Technology) (submittedVersion)
- Funders
- National Basic Research Program of China (2017YFB0802200)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Keywords
- differential privacy, privacy-preserving machine learning, Laplace mechanism, Gaussian mechanism, exponential mechanism, output perturbation, data privacy, model utility, 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
