The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Federated Learning With Differential Privacy: Algorithms and Performance Analysis
Open accessAbstract
Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients’ private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from clients, e.g., weights trained in deep neural networks. In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noise is added to parameters at the clients’ side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting different variances of artificial noise. Then we develop a theoretical convergence bound on the loss function of the trained FL model in the NbAFL. Specifically, the theoretical bound reveals the following three key properties: 1) there is a tradeoff between convergence performance and privacy protection levels, i.e., better convergence performance leads to a lower protection level; 2) given a fixed privacy protection level, increasing the number$N$of overall clients participating in FL can improve the convergence performance; and 3) there is an optimal number aggregation times (communication rounds) in terms of convergence performance for a given protection level. Furthermore, we propose a$K$-client random scheduling strategy, where$K$($1\leq K< N$) clients are randomly selected from the$N$overall clients to participate in each aggregation. We also develop a corresponding convergence bound for the loss function in this case and the$K$-client random scheduling strategy also retains the above three properties. Moreover, we find that there is an optimal$K$that achieves the best convergence performance at a fixed privacy level. Evaluations demonstrate that our theoretical results are consistent with simulations, thereby facilitating the design of various privacy-preserving FL algorithms with different tradeoff requirements on convergence performance and privacy levels.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 training algorithms62–64 allow for mitigation of information leakage from both the collaborator model updates and the global consensus aggregated models.”
From Federated learning enables big data for rare cancer boundary detection (2022) · cites this paper as [63]
In the citing paper
“When it comes to FL, to prevent information leakage the concept of DPis utilized by adding noise to the parameters that are exchanged by the participants before model aggregation at the server side [25].”
From A Review of Privacy Enhancement Methods for Federated Learning in Healthcare Systems (2023) · cites this paper as [25]
In the citing paper
“Three ML models are employed, including perceptron, support vector machine (SVM), and logistic regression, to perform FL training, showing that a competitive accuracy performance is achieved by using differential privacy-based FL methods compared to traditional FL schemes.”
From Federated learning for smart healthcare: A survey (2023) · cites this paper as [82]
In the citing paper
“This can be done by using perturbation techniques [25] such as differential privacy can be used to protect training datasets against data breach, by constructing composition theorems with complex mathematical solutions.”
From Federated learning meets blockchain in edge computing: Opportunities and challenges (2021) · cites this paper as [25]
In the citing paper
“Although some techniques have been used to overcome this problem, including differential privacy [166], these approaches degrade model performance or require additional conditions that are not suitable for IoT networks, especially high computing power [167].”
From Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis (2021) · cites this paper as [166]
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
Gradient-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
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
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
Federated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Federated Learning: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766
Introductory Lectures on Convex Optimization: A Basic Course
Нестеров, Ю. Е. (2014) · Medical Entomology and Zoology · Cited by 3,576
Cited by
Sorted by citations
A survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480
Federated learning on non-IID data: A survey
Zhu, H., Xu, J., Liu, S., & Jin, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.098 · Cited by 1,062
Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges
Khan, L. U., Saad, W., Han, Z., Hossain, E., & Hong, C. S. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3090430 · Cited by 892
Federated learning for smart healthcare: A survey
Nguyen, D. C., Pham, Q.-V., Pathirana, P. N., Ding, M., Seneviratne, A., Lin, Z., Dobre, O., & Hwang, W.-J. (2023) · ACM Computing Surveys · doi:10.1145/3501296 · Cited by 827
Self-citationA Survey on Federated Learning for Resource-Constrained IoT Devices
Imteaj, A., Thakker, U., Wang, S., Li, J., & Amini, M. H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3095077 · Cited by 774
Self-citation
Metadata
- Authors
- Wei, K., Li, J., Ding, M., Ma, C., Yang, H. H., Farokhi, F., Jin, S., Quek, T. Q. S., & Vincent Poor, H.
- Affiliations
- Nanjing University of Science and Technology (CN)
- Tomsk Polytechnic University (RU)
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Singapore University of Technology and Design (SG)
- Southeast University (CN)
- Department of Electrical Engineering, Princeton University, Princeton, NJ
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2020
- Volume
- 15
- Pages
- 3454-3469
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W3016632787
- Cited by
- 2,400
- References
- 40
- Citations by year
- 2026: 382 · 2025: 555 · 2024: 577 · 2023: 399 · 2022: 284 · 2021: 162 · 2020: 41
- FWCI
- 87.08
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Minerva Access (University of Melbourne) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key Research and Development Program of China (2018YFB1004800)
- National Natural Science Foundation of China (61872184, 61727802)
- SUTD Growth Plan Grant for AI
- U.S. National Science Foundation (CCF-1908308)
- Princeton Center for Statistics and Machine Learning under a Data X Grant
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Keywords
- federated learning, differential privacy, artificial noise, convergence bounds, privacy-utility trade-off, communication rounds, deep neural network training, information leakage
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
