A Blockchain-Based Decentralized Federated Learning Framework with Committee Consensus
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Federated learning has been widely studied and applied to various scenarios, such as financial credit, medical identification, and so on. Under these settings, federated learning protects users from exposing their private data, while cooperatively training a shared machine learning algorithm model (i.e., the global model) for a variety of realworld applications. The only data exchanged is the gradient of the model or the updated model (i.e., the local model update). However, the security of federated learning is increasingly being questioned, due to the malicious clients or central servers' constant attack on the global model or user privacy data. To address these security issues, we propose a decentralized federated learning framework based on blockchain, that is, a Block-chain-based Federated Learning framework with Committee consensus (BFLC). Without a centralized server, the framework uses blockchain for the global model storage and the local model update exchange. To enable the proposed BFLC, we also devise an innovative committee consensus mechanism, which can effectively reduce the amount of consensus computing and reduce malicious attacks. We then discuss the scalability of BFLC, including theoretical security, storage optimization, and incentives. Finally, based on a FISCO blockchain system, we perform experiments using an AlexNet model on several frameworks with a real-world dataset FEMNIST. The experimental results demonstrate the effectiveness and security of the BFLC framework.
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?
In the citing paper
“These obstacles could be overcome with swarm learning (SL), in which partners jointly train AI models while avoiding data transfer and monopolistic data governance.”
From Swarm learning for decentralized artificial intelligence in cancer histopathology (2022) · cites this paper as [25]
In the citing paper
“SL, however, offers a solution to the governance problem, providing a true collaborative and democratic approach in which partners communicate and work on the same level, jointly and equally training models and sharing the benefits 25,26,33 .”
From Swarm learning for decentralized artificial intelligence in cancer histopathology (2022) · cites this paper as [25]
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
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 · cited 1×
“Each framework performs the classic image classification model AlexNet [14] as the global model and fixed a set of model hyper-parameters to ensure fairness.”
MethodCommunication-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 3×
“In the original FL settings, FedAvg [12] aggregates all the updates into a new global model.”
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 3×
“To address the first challenge, the committee consensus mechanism could maximize the generalization ability of the global model by validating the local updates with committee members’ data distribution [1].”
BackgroundMethodInfluentialPrivacy-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 · cited 1×
“The aggregation can be performed on the local gradients [11] or the local models [12], and the network transmission consumptions of these two methods are equal.”
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Yin, D., Chen, Y., Ramchandran, K., & Bartlett, P. (2018) · arXiv · doi:10.48550/arxiv.1803.01498 · Cited by 1,130 · cited 1×
“In this sub-section, we simulate malicious node attacks to demonstrate how the proposed BFLC, basic FL, and CwMed [15] will be affected under different malicious proportions among active nodes.”
BackgroundLEAF: A Benchmark for Federated Settings
Caldas, S., Duddu, S. M. K., Wu, P., Li, T., Konečný, J., McMahan, H. B., Smith, V., & Talwalkar, A. (2018) · arXiv · doi:10.48550/arxiv.1812.01097 · Cited by 894 · cited 1×
“To demonstrate the effectiveness of the BFLC, we perform it on the real-world federated dataset FEMNIST [13].”
MethodThe Chinese University Of Hong Kong
(2004) · Computer · doi:10.1109/mc.2004.1318822 · Cited by 256
FLChain: A Blockchain for Auditable Federated Learning with Trust and Incentive
Bao, X., Su, C., Xiong, Y., Huang, W., & Hu, Y. (2019) · 2019 5th International Conference on Big Data Computing and Communications (BIGCOM) · doi:10.1109/bigcom.2019.00030 · Cited by 225 · cited 2×
“One of the related works [10] selects a leader to execute the consensus.”
BackgroundGossip Learning as a Decentralized Alternative to Federated Learning
Hegedűs, I., Danner, G., & Jelasity, M. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-22496-7_5 · Cited by 214 · cited 1×
“The study in [5] assumed that the data remains at the edge devices, but it requires no aggregation server or any central component.”
BackgroundWhen Machine Learning Meets Blockchain: A Decentralized, Privacy-preserving and Secure Design
Chen, X., Ji, J., Luo, C., Liao, W., & Li, P. (2018) · 2018 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2018.8622598 · Cited by 213 · cited 1×
“[4] propose to leverage the blockchain to record the updates from nodes and the evaluation of those updates.”
Background
Cited by
Items 601–645 of 645
FedUAV-FL: Federated Collaborative Recognition Framework for Illegal Structures Using UAV Networks
Zhang, F., Jia, W., Tan, Y., Liu, T., Jiang, Z., & Fan, Y. (2025) · International Conference on Advanced Computer Theory and Engineering · doi:10.1109/icacte66284.2025.11412074
“The core innovation lies in designing an innovative committee consensus mechanism that significantly reduces consensus computation overhead while ensuring security, and effectively resists malicious node attacks [6].”
Taeb, M., Bernadin, S., & Chi, H. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402187
“Centralized FL relies on a coordinating server [7], while decentralized FL removes this server via peer-to-peer consensus [8].”
Energy-efficient serverless federated learning with blockchain-enhanced optimized raft consensus
Lu, J., Qi, P., Yu, S., Liu, J., Cao, S., & Jin, Y. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108473 · Cited by 1
Robust Federated Learning With Double Denoising
Wei, X., Chen, S., Li, X., & Chen, S. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3673539
“FL has already achieved significant success in fields such as smart healthcare [7] and financial transactions [8].”
Gao, C., Deng, W., Zhou, N., Liang, X., & Cui, W. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133454
Privacy-preserving decentralized federated broad continuous learning based on complete binary tree
Ren, C., Cheng, S., Li, N., & Chen, C. L. P. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133437
Self-citationDesign and implementation of DFL framework based on EdgeX platform in digital twin network
Tuan, N. A., Moe, S. J. S., Khan, A. N., & Kim, D. H. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108496 · Cited by 1
Qiu, W., Gao, Q., Xiao, J., Cai, S., Xu, R., & Cao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8411-6_1
Btfl: Blockchain-based trustworthy federated learning scheme for industrial internet of things
Wang, H., Liu, D., Shen, Z., Liu, P., & Liu, K. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02858-9
Fraud Guard: Enhancing Credit card Security using Graph Neural Network Models
Bodire, S. S., Bontha, S., Maheswari, U., Ramasubbareddy, S., & Aluvalu, R. (2025) · International Conference on Advancement in Futuristic Technologies (ICAFT) · doi:10.1109/icaft66710.2025.11452969
“The primary component in the detection engine is Graph Neural Networks because they develop detailed relationships between users and merchants and their transactions, producing precise fraud predictions [6].”
DFLADMM-M: Decentralized Federated Learning via Momentum-Accelerated ADMM
Xiao, S., Yu, J., Wang, G., Liu, W., Hu, Q., & Cao, B. (2026) · International Symposium on Computer Applications and Information Systems (ISCAIS) · doi:10.1109/iscait69154.2026.11477188
“As shown in Figure 1, its decentralized nature allows for flexible and topology-adaptive learning, supporting diverse network topologies [2], making DFL a suitable fit for collaborative learning in trustless environments [6].”
Fan, W., Deng, X., Chen, Z., Zhao, M., Wu, G., Qiu, K., & Hu, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3685354
“More importantly, an untrusted or compromised server can seriously threaten the security and integrity of the entire system, thereby weakening the willingness of clients to participate [6].”
Salihovic, A., Abdisarabshali, P., Langberg, M., & Hosseinalipour, S. (2026) · npj Wireless Technology · doi:10.1038/s44459-025-00022-x · Cited by 1
FedBlockSiamese: Federated Learning with Blockchain for Medical Images with Siamese Network
Anusuya, R., & Karthika Renuka, D. (2026) · Journal of Intelligent & Fuzzy Systems · doi:10.1177/18758967261438599
“The decentralized environment offered by blockchain (Li et al., 2021; Liu et al., 2020; Lu et al., 2020; Moudoud & Cherkaoui, 2023) and Federated Learning helps in applications like healthcare where multiple hospitals must collaboratively train their data.”
Abdel-lah, M., Hesham, A., Salah, A., & Behery, G. M. (2026) · Information · doi:10.3390/info17060528
Molose, R. R. S., Isong, B., Abu-Mahfouz, A. M. I., & Dladlu, N. (2025) · IEEE AFRICON · doi:10.1109/africon66545.2025.11533780
“…malicious behaviour [27], homomorphic encryption to protect during computation, [28, 29], blockchain to prevent parameter tampering, and secure multi-party computation to secure model updates [30, 31], and differential privacy which adds noise to model updates to prevent data leakage [24-26].”
Jain, S., & Kumar, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-20606-0_33
BSFL: Secure and Efficient Blockchain-Based Split Federated Learning for Internet of Vehicles
Jiang, Z., Chi, C., Liu, Y., Du, H., Jia, Z., Tairan, D., Wu, Q., Guan, Z., Li, D. S., & Susilo, W. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3695964
“Li et al. [12] introduced a decentralized FL scheme called BFLC based on blockchain.”
吴, 毓. (2026) · Computer Science and Application · doi:10.12677/csa.2026.165179
Zi, Y., & Zhou, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-53140-z
AbdelRaouf, H., El-Toukhy, A. T., Fouda, M. M., Fadlullah, Z. M., & Ibrahem, M. I. (2026) · IEEE International Conference on Secure IoT, Assured and Trusted Computing (SATC) · doi:10.1109/satc69565.2026.11542261
Kuang, Y., Chen, J., Zhang, Y., Chen, X., Chen, S., & Liu, X. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108642 · Cited by 2
AI and Blockchain Integration for Cybersecurity
Ramachandran, M. (2026) · Texts in computer science · doi:10.1007/978-3-032-25874-8_2
Linda, C. H., & Griffin, S. D. (2026) · International Conference on Sustainable and Futuristic Technologies (ICSFT) · doi:10.1109/icsft67370.2026.11566540
“In 2020, Li, Y., et.al, [14] suggested a decentralized federated learning framework with the aid of blockchain and committee consensus algorithms.”
DCMF-BFL: A decentralized consensus multi-factor approach for blockchain-based federated learning
Ma, G., Zeng, Z., Bhuyan, M. H., Qi, S., & Liu, Y. (2026) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2026.105305
Zhou, Q., Mao, X., & Chen, Y. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123859
DecentFL: A Decentralized Federated Learning System With Multiple Aggregators and Evaluators
Syed, K. H., Poghosyan, R., Shi, H., Ma, R., Luo, Y., Bassam, E., Zhou, Z., Qu, Z., & Guan, H. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3710438
“Similarly, Li et al. [25] introduced an alliance blockchain architecture in which a committee of nodes performs aggregation and validation.”
Blockchain-Based Framework for Segmented Gossip Learning in Decentralized Systems
Turazza, F., Pietri, M., & Hadjidimitriou, N. S. (2026) · Proceedings of the 2026 International conference on Infrastructure-as-a-Service (IaaS) and Platform-as-a-Service (PaaS) solutions for Europe's Next-Gen Cloud Infrastructure · doi:10.1145/3793828.3793836
“Frameworks like FLchain [2], BFLC [10], and BlockFL [9] employ blockchain to enhance decentralization and transparency.”
Empowering Industrial Federated Learning: Blockchain-Based Model Validation and Incentive Mechanism
Jiang, X., Cheng, Y., Yang, J., Song, Z., Yang, Z., & Yao, L. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3711890
“Li et al. [31] proposed an approach in the decentralized federated learning framework where an elected committee evaluates the local model of each client and assigns incentives based on the model’s accuracy.”
NeuralFortress-XFL: Privacy-Preserving Federated Explainable Learning for Cyber Threat Intelligence
Binbusayyis, A. (2026) · Electronics · doi:10.3390/electronics15143124
Kamble, A. S., & Sarda, E. (2026) · International Journal on Smart Sensing and Intelligent Systems · doi:10.2478/ijssis-2026-0043
L-SDFL: A Lightweight Semi-Distributed Federated Learning for Communication Efficiency
Qu, D., Li, L., Li, R., Liu, X., Wang, H., & Min, G. (2026) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/2575-8411.2026.00057
“Based on the interaction patterns, existing methods can be categorized into three types: blockchain-based distributed FL algorithms [5], [9]–[12], protocol-based distributed FL algorithms [8], [13], [14], and client interaction-based distributed FL algorithms [6], [7], [15], [16].”
Liu, C., Shen, H., Law, E. K. L., & Lam, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-9846-5_37
Liu, C., Shen, H., Law, E. K. L., & Lam, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-9846-5_29
A Blockchain-driven and Verifiable Collaborative Paradigm for Federated Learning
Chen, F., & Li, Y. (2025) · International Conference on Data Management and Computer Science (ICDMCS) · doi:10.1109/icdmcs69443.2025.00017
“Our baselines included Centralized FedAvg, BFLC [3], and FLChain [9].”
Self-citationA Secure and Verifiable Federated Learning Framework for Industrial Internet Systems
Bu, Z., Wen, M., & Tian, Y. (2026) · International Conference on Electronic Technology and Information Science (ICETIS) · doi:10.1109/icetis70504.2026.11633430
“However, blockchain demands high resources unsuitable for constrained IIoT devices [12], and signatures face scalability issues as participants grow [7], [13].”
Nyapete, M. N., Omollo, R. O., & Masinde, N. W. (2026) · Journal of Computer and Communications · doi:10.4236/jcc.2026.148002
Fu, X., Li, J., Zhong, H., Wang, D., Chen, W., & Li, F. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.101049
Ferreira, T., & Duraes, J. A. (2026) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan15050072
Zhang, X., Wang, W., Zhang, K., & Du, G. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-37274-1_27
RetFL: a privacy-preserving and traceable framework for robust federated learning
Huang, Y., Zhou, Z., Tian, Y., Chen, C., Luo, H., & Li, T. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01301-5
“This increases communication, computation, and gas costs Fotohi et al. (2024); Li et al. (2020b).”
Self-citationNEXT-GEN Device Security: Scalable Trust-Chain with Adaptive Consensus for Optimized Security
Shashidhara, R., Singhania, A., Nair, R. C., & Verma, N. (2026) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct68978.2026.11700753
“The private blockchain ensures tamper-proof device data, while localization enables accurate tracking and context-aware automation [15], [16].”
Patil, S., Shaikh, Z., Kadlak, N., Gandule, P., Janbandhu, V., Gosavi, G., & Karale, P. (2026) · International Conference on Innovation & Growth in Next-Gen Intelligent Technology & Engineering (IGNITE) · doi:10.1109/ignite69592.2026.11706023
Wang, Z., Irvan, M., Perera, M. N. S., Kobayashi, R., & Yamaguchi, R. S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38708-0_32
Tran, K. T., Minh, K. B., Nguyen, K. M., & Le, T. T. B. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6840-5_23
Metadata
- Authors
- Li, Y., Chen, C., Liu, N., Huang, H., Zheng, Z., & Yan, Q.
- Affiliations
- Sun Yat-sen University (CN)
- WeBank Co. Ltd.
- Venue
- IEEE Network
- Published
- 2021-01
- Volume
- 35
- Issue
- 1
- Pages
- 234-241
- ISSN
- 0890-8044 (ISSN-L)
- 1558-156X
- OpenAlex
- W3014517104
- Cited by
- 645
- References
- 18
- Citations by year
- 2026: 71 · 2025: 132 · 2024: 167 · 2023: 148 · 2022: 82 · 2021: 38
- FWCI
- 27.01
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Network (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key Research and Development Program (2016YFB1000101)
- National Natural Science Foundation of China (11801595,61722214)
- Natural Science Foundation of Guangdong (2018A030310076,2019A1515011043)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Keywords
- federated learning, blockchain, decentralized learning, malicious clients, privacy preservation, consensus algorithms, scalability, incentives, AlexNet
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.