More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence
Open accessThe DOI matches its Crossref record; 151 of the 152 references it cites were found in a registry or an index.
Abstract
Artificial Intelligence (AI) has attracted a great deal of attention in recent years. However, alongside all its advancements, problems have also emerged, such as privacy violations, security issues and model fairness. Differential privacy, as a promising mathematical model, has several attractive properties that can help solve these problems, making it quite a valuable tool. For this reason, differential privacy has been broadly applied in AI but to date, no study has documented which differential privacy mechanisms can or have been leveraged to overcome its issues or the properties that make this possible. In this paper, we show that differential privacy can do more than just preserve privacy. It can also be used to improve security, stabilize learning, build fair models, and impose composition in selected areas of AI. With a focus on regular machine learning, distributed machine learning, deep learning, and multi-agent systems, the purpose of this article is to deliver a new view on many possibilities for improving AI performance with differential privacy techniques.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The data that is collected or used by third parties, without the authorization or voluntary consent of individuals, would result in the violations of their privacy (Wu et al., 2022;Zhu et al., 2020).”
From Artificial intelligence governance: Ethical considerations and implications for social responsibility (2024) · cites this paper as Zhu et al., 2020
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Differential privacy [17, 18] guarantees that by looking at a model output, one cannot tell whether a sample is in the training dataset or not.”
From Machine Unlearning: A Survey (2024) · cites this paper as [17]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512
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
Intelligent agents: theory and practice
Wooldridge, M., & Jennings, N. R. (1995) · The Knowledge Engineering Review · doi:10.1017/s0269888900008122 · Cited by 6,810 · cited 1×
“domain problems [99], [100].”
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
Federated 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 · cited 1×
“Federated learning was first proposed by Google in 2017 as an additional approach to the standard centralised machine learning approaches [78], and has been applied to several real-world applications [79].”
BackgroundA Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
Dwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291
Research works printed but not linked: 12
- Russell, 2002, Artificial Intelligence: A Modern Approach
- 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
- Chaudhuri, 2011, Differentially private empirical risk minimization, J. Mach. Learn. Res., 12, 1069
- Nobel, 2018, Algorithms of Oppression: How Search Engines Reinforce Racism, 10.18574/nyu/9781479833641.001.0001 · DOI · Paper page
- Zemel, Learning fair representation, III-325
- Dwork, Fairness under composition, 33:1
- Zhao, Distributed deep learning under differential privacy with the teacher-student paradigm, 404
- 10.1145/3298981 · DOI · Paper page
- Bhagoji, Analyzing federated learning through an adversarial lens, 634
- 10.1145/2660267.2660348 · DOI · Paper page
- Bonanno, 2018, Game Theory
- 10.1145/2976734 · DOI
Cited by
Items 201–219 of 219
IFAA: An Improved Field Anonymity Algorithm for Efficient Big Data Privacy Preservation
Sun, M., Zhao, X., Liu, Z., Xiao, Y., Zhang, R., & Tang, Y. (2025) · International Conference on Big Data, Artificial Intelligence and Risk Management (ICBAR) · doi:10.1145/3800227.3800287
“While DP provides provable privacy guarantees, the added noise inevitably degrades the accuracy of analytical results [3, 23].”
Differentially Private Deep Learning for Smartphone-Based Human Activity Recognition
Sarkar, I., Bagchi, A. K., & Shahriar, M. S. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491348
“Wang et al. [17] investigated noise addition to feature vectors to achieve local differential privacy but reported significant accuracy loss.”
Musha, A., Islam, A., & Ghosh, T. (2025) · IEEE International Conference on Biomedical Engineering, Computer and Information Technology for Health (BECITHCON) · doi:10.1109/becithcon69222.2025.11504211
“Various techniques have been employed to ensure privacy during data analysis, including differential privacy (DP) [6], [7], cryptographic primitives - secure multi-party computation (SMPC) [8], [9], and homomorphic encryption [10].”
Xu, M., Li, J., & Chen, Y. (2026) · Transactions of the Institute of Measurement and Control · doi:10.1177/01423312261443361
Fouzdar, A., Geetha, Y., Batra, V., Kukreti, A., Patidar, D., & Shukla, P. K. (2025) · IEEE International Conference on Recent Trends in Computing and Smart Mobility (RCSM) · doi:10.1109/rcsm67767.2025.11507717
“In a different study, Patel and Sharma (2023) [13] used FL to real-time prediction of traffic flows in various districts and the results showed a 19 percent reduction in latency and 23 percent improvement in privacy over conventional models.”
Explainability-guided spatiotemporal adaptive differential privacy for graph neural networks
He, C., Xiao, S., 陈恒波, Ding, Y., & 陈恒波 (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116195
Kanaan, M. A., Chicha, E., Couchot, J.-F., & Assaf, M. A. (2026) · IEEE Middle East and North Africa Communications Conference (MENACOMM) · doi:10.1109/menacomm69507.2026.11532823
“One way to address privacy issues is through the integration of Differential Privacy (DP) [2], [3], which is based on the concept of adding noise into machine learning algorithms.”
Xie, L., Wang, Y., Wang, H., & Cui, L. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3697399
“DespitetheconsiderablepromiseofFLinpracticalappli-cations,existingresearchindicatesthattransmittinglocalup-datestotheFLserverisvulnerabletoprivacyattacks,such asinferenceattacks,whichcanleadtoprivacybreacheson theclientside[12].”
6G network security and privacy issues
Shree, K. D., Karthiga, M., Ranjeethapriya, K., Shobana, G., Saranya, K., & Umamageswari, D. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-33700-0.00009-1
Differential privacy-enabled neural networks for secure credit risk forecasting in banking
Naresh, V. S., Reddi, S., & Thamarai, M. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08605-3
“The analysis of differential privacy in deep learning applications was discussed in [11, 12].”
Pan, Y.-L., Yu, P.-F., Yin, X.-L., Hong-sheng, Y., Long, X., & Tong, Q. (2026) · Educational Technology Research and Development · doi:10.1007/s11423-026-10659-2 · Cited by 2
Self-citationTrust by design: Human factors and trust calibration in ML-based educational systems
Anthis, Z., & Kyriakidou-Zacharoudiou, A. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103893
Partial Privacy for Sensitive Subsets in Deep Learning Models
Shateri, M., & Sayedana, B. (2026) · Conference proceedings - Canadian Conference on Electrical and Computer Engineering · doi:10.1109/ccece68150.2026.11610092
Dai, J., & Li, S. (2026) · Journal of Management Analytics · doi:10.1080/23270012.2026.2640589
Wang, L., Zhu, J., & Zheng, C. (2026) · Journal of the Operational Research Society · doi:10.1080/01605682.2026.2710391
Leveraging privacy-preserving methods in the detection of advanced persistent threats and ransomware
Khule, M., Motwani, D., & Chauhan, D. (2026) · Cluster Computing · doi:10.1007/s10586-026-06472-4
Bindra, J. S., Chaturvedi, H., Singh, S., & Singh, S. K. (2026) · International Conference on NextGen Data Science and Analytics (ICNDSA) · doi:10.1109/icndsa68777.2026.11652307
“At the same time, strict transparency and data governance must be incorporated into AI´s integration within the legal area to meet growing ethical and privacy issues [16, 17, 25].”
EdurLDP-FL: Differential privacy for accelerated convergence in federated learning
Jia, H., Wang, Z., Yan, X., Tang, Y., & Li, Q. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112715
Comparing Vertical Federated Learning Frameworks in Manufacturing Supply Chains
Kallisch, J., Gómez, J. M., & Wunck, C. (2026) · Progress in IS · doi:10.1007/978-3-032-14099-9_28
Metadata
- Authors
- Zhu, T., Ye, D., Wang, W., Zhou, W., & Yu, P. S.
- Affiliations
- China University of Geosciences (CN)
- University of Technology Sydney (AU)
- University of Illinois Chicago (US)
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2022-06-01
- Volume
- 34
- Issue
- 6
- Pages
- 2824-2843
- ISSN
- 1041-4347 (ISSN-L)
- 1558-2191
- 2326-3865
- OpenAlex
- W3047327820
- Semantic Scholar
- 7d5b94f9d2cee5823757352155d0234454f09a0e
- Cited by
- 219
- References
- 152
- Citations by year
- 2026: 27 · 2025: 64 · 2024: 45 · 2023: 36 · 2022: 23
- FWCI
- 8.08
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- IEEE Transactions on Knowledge and Data Engineering (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- OPUS - Open Publications of UTS Scholars (University of Technology Sydney) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61972366)
- National Science Foundation (III-1526499, III-1763325, III-1909323, SaTC-1930941)
- Australian Research Council Discovery (DP190100981)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
- Keywords
- differential privacy, privacy preservation, machine learning security, model fairness, distributed learning, deep learning, multi-agent systems, learning stability, 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.