Practical and Robust Federated Learning With Highly Scalable Regression Training
Open accessThe DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Abstract
Privacy-preserving federated learning, as one of the privacy-preserving computation techniques, is a promising distributed and privacy-preserving machine learning (ML) approach for Internet of Medical Things (IoMT), due to its ability to train a regression model without collecting raw data of data owners (DOs). However, traditional interactive federated regression training (IFRT) schemes rely on multiple rounds of communication to train a global model and are still under various privacy and security threats. To overcome these problems, several noninteractive federated regression training (NFRT) schemes have been proposed and applied in a variety of scenarios. However, there are still several challenges: 1) how to protect the privacy of DOs' local dataset; 2) how to realize highly scalable regression training without linear dependence on sample dimension; 3) how to tolerate DOs' dropout; and 4) how to enable DOs to verify the correctness of aggregated results returned from the cloud service provider (CSP). In this article, we propose two practical noninteractive federated learning schemes with privacy-preserving for IoMT, named homomorphic encryption based NFRT (HE-NFRT) and double-masking protocol based NFRT (Mask-NFRT), respectively, which are based on a comprehensive consideration of NFRT, privacy concerns, high-efficiency, robustness, and verification mechanism. The security analyses display that our proposed schemes are able to protect the privacy of DOs' local training data, resist collusion attack, and support strong verification to each DO. The performance evaluation results demonstrate that our proposed HE-NFRT scheme is desirable for a high-dimensional and high-security IoMT application while Mask-NFRT scheme is desirable for a high-dimensional and large-scale IoMT application.
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
Figures





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 cited source says what the claim attributes to it.
In the citing paper
“FL allows ML model training while preserving data privacy [35,36,37]”
From A Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models (2024) · cites this paper as [36]
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
Self-citationNew directions in cryptography
Diffie, W., & Hellman, M. (1976) · IEEE Transactions on Information Theory · doi:10.1109/tit.1976.1055638 · Cited by 14,713
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 · cited 2×
“To solve the above problems, federated learning [6], [7] is a promising distributed ML approach for IoMT, in which raw data are kept with DOs.”
BackgroundShamir, A. (1979) · Communications of the ACM · doi:10.1145/359168.359176 · Cited by 13,756 · cited 9×
“In particular, PrivFL [9], VerifyNet [17], and VeriFL [18] use secret sharing protocol [24] to tolerate users’ dropout.”
BackgroundMethodInfluentialPractical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956 · cited 5×
“How to design a robust NFRT scheme is challenging [9], [16], [17], [18].”
BackgroundMethodInfluentialFederated 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 · cited 1×
“To solve the above problems, federated learning [6], [7] is a promising distributed ML approach for IoMT, in which raw data are kept with DOs.”
BackgroundTowards Federated Learning at Scale: System Design
Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konečný, J., Mazzocchi, S., McMahan, H. B., et al. (2019) · arXiv · doi:10.48550/arxiv.1902.01046 · Cited by 2,334 · cited 2×
“3) Robustness: In IoMT applications, it is common for DOs to unable to upload data to the CSP in time due to battery problems and unreliable networks [15].”
BackgroundSecureML: A System for Scalable Privacy-Preserving Machine Learning
Mohassel, P., & Zhang, Y. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.12 · Cited by 1,936 · cited 10×
“Although NFRT has been researched in recent works [10], [11], [12], [13], to address the above problems, there are still some challenges.”
BackgroundMethodInfluentialAggregate and Verifiably Encrypted Signatures from Bilinear Maps
Boneh, D., Gentry, C., Lynn, B., & Shacham, H. (2003) · Lecture Notes in Computer Science · doi:10.1007/3-540-39200-9_26 · Cited by 1,821 · cited 1×
“VerifyNet [17], VeriFL [18], PVFL [21], and VFL [22] support verification to each user by linear homomorphic hash [45] or bilinear aggregate signature [46].”
MethodRobust and Communication-Efficient Federated Learning From Non-i.i.d. Data
Sattler, F., Wiedemann, S., Muller, K.-R., & Samek, W. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2944481 · Cited by 1,725 · cited 2×
“However, these schemes [42], [43], [44] still involve multiple round interactive communications between users and the server.”
BackgroundPrivacy-Preserving Deep Learning via Additively Homomorphic Encryption
Phong, L. T., Aono, Y., Hayashi, T., Wang, L., & Moriai, S. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2787987 · Cited by 1,662
How to Generate Cryptographically Strong Sequences of Pseudorandom Bits
Blum, M., & Micali, S. (1984) · SIAM Journal on Computing · doi:10.1137/0213053 · Cited by 1,322
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Lin, Y., Han, S., Mao, H., Wang, Y., & Dally, W. J. (2017) · arXiv · doi:10.48550/arxiv.1712.01887 · Cited by 1,134 · cited 2×
“However, these schemes [42], [43], [44] still involve multiple round interactive communications between users and the server.”
BackgroundSelf-citationBeyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Wang, Z., Song, M., Zhang, Z., Song, Y., Wang, Q., & Qi, H. (2019) · IEEE INFOCOM 2019 - IEEE Conference on Computer Communications · doi:10.1109/infocom.2019.8737416 · Cited by 881
Self-citationVerifynet: Secure and verifiable federated learning
Xu, G., Li, H., Liu, S., Yang, K., & Lin, X. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2929409 · Cited by 839 · cited 10×
“…Mask-NFRT schemes are only O ( m ) (i.e., dimension-independent), while that of VANE [13] are O (( d + 1 ) ) , and those of PrivFL [9], VerifyNet [17], and VeriFL [18] are O (( d + 1 ) · m ) , where d is the dimension of each sample and m is the number of selected DOs, which significantly saves…”
BackgroundMethodResultInfluentialDisease variant prediction with deep generative models of evolutionary data
Frazer, J., Notin, P., Dias, M., Gomez, A., Min, J. K., Brock, K., Gal, Y., & Marks, D. S. (2021) · Nature · doi:10.1038/s41586-021-04043-8 · Cited by 791
Efficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence
Hao, M., Li, H., Luo, X., Xu, G., Yang, H., & Liu, S. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2945367 · Cited by 569 · cited 10×
“For industrial artificial intelligence, Hao et al. [12] excogitated a federated learning scheme with privacy-enhanced and noninteractive, named PEFL.”
BackgroundMethodInfluentialHardy, S., Henecka, W., Ivey-Law, H., Nock, R., Patrini, G., Smith, G., & Thorne, B. (2017) · arXiv · doi:10.48550/arxiv.1711.10677 · Cited by 431 · cited 1×
“In the logistic regression model, the loss function can be approximated by the L 2-norm regularization and second-order Taylor series [23] as Then, for the ϕ th round and j = 1 , 2 , . . . , d , we have The same as linear regression, the iterative operation terminates until meeting the termination…”
MethodVeriFL: Communication-Efficient and Fast Verifiable Aggregation for Federated Learning
Guo, X., Liu, Z., Li, J., Gao, J., Hou, B., Dong, C., & Baker, T. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3043139 · Cited by 314
Incremental Cryptography: The Case of Hashing and Signing
Bellare, M., Goldreich, O., & Goldwasser, S. (2007) · Lecture Notes in Computer Science · doi:10.1007/3-540-48658-5_22 · Cited by 312 · cited 1×
“VerifyNet [17], VeriFL [18], PVFL [21], and VFL [22] support verification to each user by linear homomorphic hash [45] or bilinear aggregate signature [46].”
MethodVFL: A Verifiable Federated Learning With Privacy-Preserving for Big Data in Industrial IoT
Fu, A., Zhang, X., Xiong, N., Gao, Y., Wang, H., & Zhang, J. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3036166 · Cited by 288
Smart and Practical Privacy-Preserving Data Aggregation for Fog-Based Smart Grids
Zhao, S., Li, F., Li, H., Lu, R., Ren, S., Bao, H., Lin, J.-H., & Han, S. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3014487 · Cited by 195 · cited 2×
“…of honest-but-curious, which has been commonly used in privacy-preserving ML schemes [26], [27] and other privacy-preserving computation areas [14], [28], [29], we rede-fine the definition of honest-but-curious as below: Definition 1 (Honest-But-Curious): Apart from honestly enforcing…”
BackgroundSelf-citationPrivacy-preserving distributed linear regression on high-dimensional data
Gascón, A., Schoppmann, P., Balle, B., Raykova, M., Doerner, J., Zahur, S., & Evans, D. (2017) · Proceedings on Privacy Enhancing Technologies · doi:10.1515/popets-2017-0053 · Cited by 193 · cited 1×
“Gascón et al. [38] proposed a privacy-preserving protocol for computing linear regression models, where the training dataset is vertically distributed among multiple parties.”
Gu, B., Xu, A., Huo, Z., Deng, C., & Huang, H. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3072238 · Cited by 163 · cited 1×
“Different from the general definition of honest-but-curious, which has been commonly used in privacy-preserving ML schemes [26], [27] and other privacy-preserving computation areas [14], [28], [29], we rede-fine the definition of honest-but-curious as below: Definition 1 (Honest-But-Curious): Apart…”
MethodA Privacy-Preserving and Verifiable Federated Learning Scheme
Zhang, X., Fu, A., Wang, H., Zhou, C., & Chen, Z. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9148628 · Cited by 158 · cited 6×
“However, these schemes [9], [17], [18], [21], [22] belong to the traditional IFRT scheme, which relies on multiple round communications to train a global model.”
BackgroundMethodInfluentialPrivacy preserving multi-party computation delegation for deep learning in cloud computing
Ma, X., Zhang, F., Chen, X., & Shen, J. (2018) · Information Sciences · doi:10.1016/j.ins.2018.05.005 · Cited by 138 · cited 2×
“4) Verification Mechanism for the Correctness of Aggre-gated Results: For some illegal interests, the CSP is able to impact the accuracy of the trained model by fabricating the aggregated results or cut down the aggregation operations directly to reduce computational overhead [19].”
BackgroundPPM-HDA: Privacy-Preserving and Multifunctional Health Data Aggregation With Fault Tolerance
Han, S., Zhao, S., Li, Q., Ju, C.-H., & Zhou, W. (2016) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2472369 · Cited by 115
Self-citationWang, F., Zhu, H., Lu, R., Zheng, Y., & Li, H. (2020) · Information Sciences · doi:10.1016/j.ins.2020.12.007 · Cited by 93 · cited 10×
“Although NFRT has been researched in recent works [10], [11], [12], [13], to address the above problems, there are still some challenges.”
BackgroundMethodInfluentialPractical One-Shot Federated Learning for Cross-Silo Setting
Li, Q., He, B., & Song, D. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/205 · Cited by 93
(2017) · doi:10.1587/transinf.2015inp0020 · Cited by 89 · cited 1×
“Aono et al. [41] put forward a secure system for privacy-preserving training and predicting data in logistic regression via homomorphic encryption.”
BackgroundPrivacy-preserving ridge regression on distributed data
Chen, Y.-R., Rezapour, A., & Tzeng, W.-G. (2018) · Information Sciences · doi:10.1016/j.ins.2018.03.061 · Cited by 89
Mandal, K., & Gong, G. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Cloud Computing Security Workshop · doi:10.1145/3338466.3358926 · Cited by 89 · cited 10×
“Mandal and Gong [9] presented a comprehensive privacy-preserving protocol for linear, ridge, and logistic regression training, named PrivFL.”
BackgroundMethodInfluentialHow NFTs could transform health information exchange
Kostick, K. M., Mandl, K. D., Minssen, T., Cohen, I. G., Gasser, U., Kohane, I. S., & McGuire, A. L. (2022) · Science · doi:10.1126/science.abm2004 · Cited by 65
Collaborative Machine Learning: Schemes, Robustness, and Privacy
Wang, J., Pal, A., Yang, Q., Kant, K., Zhu, K., & Guo, S. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3169347 · Cited by 54 · cited 1×
“Different from the general definition of honest-but-curious, which has been commonly used in privacy-preserving ML schemes [26], [27] and other privacy-preserving computation areas [14], [28], [29], we rede-fine the definition of honest-but-curious as below: Definition 1 (Honest-But-Curious): Apart…”
MethodPrivacy-Preserving Linear Regression on Distributed Data by Homomorphic Encryption and Data Masking
Qiu, G., Gui, X., & Zhao, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3000764 · Cited by 48 · cited 1×
“For performing privacy-preserving linear regression on horizontally partitioned data, Qiu et al. [39] designed a protocol, where two servers are able to decide the global model without learning any information about the raw data.”
BackgroundZhao, S., Xu, S., Han, S., Ren, S., Wang, Y., Chen, Z., Chen, X., Lin, J., & Liu, W. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3309132 · Cited by 47 · cited 1×
“…which has been commonly used in privacy-preserving ML schemes [26], [27] and other privacy-preserving computation areas [14], [28], [29], we rede-fine the definition of honest-but-curious as below: Definition 1 (Honest-But-Curious): Apart from honestly enforcing agreements and…”
BackgroundSelf-citationLocation Privacy-Preserving Distance Computation for Spatial Crowdsourcing
Han, S., Lin, J., Zhao, S., Xu, G., Ren, S., He, D., Wang, L., & Shi, L. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2985454 · Cited by 46 · cited 1×
“…honest-but-curious, which has been commonly used in privacy-preserving ML schemes [26], [27] and other privacy-preserving computation areas [14], [28], [29], we rede-fine the definition of honest-but-curious as below: Definition 1 (Honest-But-Curious): Apart from honestly enforcing agreements…”
BackgroundSelf-citationFocus, Fusion, and Rectify: Context-Aware Learning for COVID-19 Lung Infection Segmentation
Wang, R., Ji, C., Zhang, Y., & Li, Y. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3126305 · Cited by 42
Privacy-Preserving Multiparty Learning for Logistic Regression
Du, W., Li, A., & Li, Q. (2018) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-01701-9_30 · Cited by 23
Privacy-Preserving Multiple Linear Regression of Vertically Partitioned Real Medical Datasets
Kikuchi, H., Hamanaga, C., Yasunaga, H., Matsui, H., Hashimoto, H., & Fan, C. (2018) · Journal of Information Processing · doi:10.2197/ipsjjip.26.638 · Cited by 17
Parkinsons Telemonitoring Data Set
Zhang, X. (2022) · Figshare · doi:10.6084/m9.figshare.19322537 · Cited by 6
Efficient and Secure Outsourced Linear Regression
Yang, H., He, W., Zhou, Q., & Li, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05057-3_7 · Cited by 5 · cited 10×
“Although NFRT has been researched in recent works [10], [11], [12], [13], to address the above problems, there are still some challenges.”
BackgroundMethodInfluential
Research works printed but not linked: 2
- L. Yann, C. Corinna, and J. B. Christopher. (1998). The MNIST Database of Handwritten Digits. [Online]. Available: http://yann.lecun.com/ exdb/mnist/
- Z. Huang, W.-J. Lu, C. Hong, and J. Ding, "Cheetah: Lean and fast secure two-party deep neural network inference," in Proc. USENIX Secur., 2022, pp. 1-4. [Online]. Available: http://ia.cr/2022/207
Cited by
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A. (2024) · Cognitive Computation · doi:10.1007/s12559-023-10179-8 · Cited by 2,495
“So , along with a strong foundation, necessary amendments will always help in adding more to the structure of XAI, which will lead to a greater impact [94, 95].”
BackgroundA Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models
Heidari, A., Navimipour, N. J., Dag, H., Talebi, S., & Unal, M. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10255-7 · Cited by 164
Denial of service attacks in edge computing layers: Taxonomy, vulnerabilities, threats and solutions
Uddin, R., Kumar, S., & Chamola, V. (2023) · Ad Hoc Networks · doi:10.1016/j.adhoc.2023.103322 · Cited by 124
Uddin, M. P., Xiang, Y., Hasan, M., Bai, J., Zhao, Y., & Gao, L. (2025) · ACM Computing Surveys · doi:10.1145/3727643 · Cited by 135
Hanafi, A. V., Ghaffari, A., Rezaei, H., Valipour, A., & Arasteh, B. (2023) · Cluster Computing · doi:10.1007/s10586-023-04102-x · Cited by 89
“Support Vector Machine [12], K-Nearest Neighbor (KNN) [24], decision tree, Random Forest (RF) [25], and simple Bayesian are examples of approaches that can be used in machine learning [26, 27].”
Metadata
- Authors
- Han, S., Ding, H., Zhao, S., Ren, S., Wang, Z., Lin, J., & Zhou, S.
- Affiliations
- Hangzhou City University (CN)
- Zhejiang Gongshang University (CN)
- Zhejiang University (CN)
- Zhejiang Ponshine Information Technology Company Ltd., Hangzhou, China
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2024-10
- Volume
- 35
- Issue
- 10
- Pages
- 13801-13815
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W4379805355
- Cited by
- 60
- References
- 42
- Citations by year
- 2026: 9 · 2025: 16 · 2024: 15
- FWCI
- 5.66
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (62072403, U20A20182, 61906167)
- Zhejiang Provincial Natural Science Foundation of China (LQ22F020001, LTY21F020001)
- Ministry of Education Humanities and Social Sciences General Project (22JDSZ3124)
- Scientific Research Fund of Zhejiang Provincial Education Department (Y202147355)
- Laboratory Work Research Project of Universities in Zhejiang (20220003)
- “Pioneer” and “Leading Goose” R&D Program of Zhejiang (2022C01243)
- Key Research and Development Program of Zhejiang Province (2020C01076)
- 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 federated learning, Internet of Medical Things, homomorphic encryption, collusion resistance, scalability, high-dimensional data, cloud service provider security
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.