Blockchained On-Device Federated Learning
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
By leveraging blockchain, this letter proposes a blockchained federated learning (BlockFL) architecture where local learning model updates are exchanged and verified. This enables on-device machine learning without any centralized training data or coordination by utilizing a consensus mechanism in blockchain. Moreover, we analyze an end-to-end latency model of BlockFL and characterize the optimal block generation rate by considering communication, computation, and consensus delays.
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
“Such that, the DFL clients can communicate via blockchain ledgers where model updates can be offloaded to the blockchain for secure model exchange and aggregation [38].”
From Federated Learning for Internet of Things: A Comprehensive Survey (2021) · cites this paper as [38]
In the citing paper
“To further avoid malicious edge servers, blockchain technology was utilized to provide a decentralized consensus environment to guarantee the validity of global models in every learning iteration.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [172]
In the citing paper
“While blockchain removes the need for a trusted curator and connects each participant through multiparty data retrieval, it also strengthens the data-sharing scheme and provides some fault-tolerant guarantees [83].”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [83]
In the citing paper
“For example, an integrated FL-blockchain scheme is proposed in [27], where both local training and global model updating are performed at mobile devices via the blockchain in the MEC network.”
From Federated learning meets blockchain in edge computing: Opportunities and challenges (2021) · cites this paper as [27]
In the citing paper
“Most of current solutions [27], [28] rely on the PoW consensus mechanism, which often requires large bandwidth and energy resources to implement the mining process.”
From Federated learning meets blockchain in edge computing: Opportunities and challenges (2021) · cites this paper as [27]
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
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
Federated Optimization: Distributed Machine Learning for On-Device Intelligence
Konečný, J., McMahan, H. B., Ramage, D., & Richtárik, P. (2016) · arXiv · doi:10.48550/arxiv.1610.02527 · Cited by 1,563
Information propagation in the Bitcoin network
Decker, C., & Wattenhofer, R. (2013) · IEEE P2P 2013 Proceedings · doi:10.1109/p2p.2013.6688704 · Cited by 1,192
Federated Learning: Collaborative Machine Learning without Centralized Training Data
A, A. V., Binny, S., R, J. T., Raj, N., & Thomas, V. (2022) · international journal of engineering technology and management sciences · doi:10.46647/ijetms.2022.v06i05.052 · Cited by 489
Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications
Samarakoon, S., Bennis, M., Saad, W., & Debbah, M. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2019.2956472 · Cited by 459
Self-citationCommunication-Efficient Distributed Optimization using an Approximate Newton-type Method
Shamir, O., Srebro, N., & Zhang, T. (2013) · arXiv · doi:10.48550/arxiv.1312.7853 · Cited by 424
Wireless Access for Ultra-Reliable Low-Latency Communication: Principles and Building Blocks
Popovski, P., Nielsen, J. J., Stefanovic, C., Carvalho, E. D., Strom, E., Trillingsgaard, K. F., Bana, A.-S., Kim, D. M., Kotaba, R., Park, J., et al. (2018) · IEEE Network · doi:10.1109/mnet.2018.1700258 · Cited by 390
Self-citationOn Security Analysis of Proof-of-Elapsed-Time (PoET)
Chen, L., Xu, L., Shah, N., Gao, Z., Lu, Y., & Shi, W. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-69084-1_19 · Cited by 351
Luong, N. C., Xiong, Z., Wang, P., & Niyato, D. (2018) · 2018 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2018.8422743 · Cited by 229
Bitcoin: A Peer-to-Peer Electronic Cash System
Portillo, N. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4993270 · Cited by 200
Research works printed but not linked: 2
- 10.1109/JPROC.2019.2941458 · DOI · Paper page
- bennis, 2018, Ultra-reliable and low-latency wireless communication: Tail, risk and scale, arXiv 1801 01270
Cited by
Items 601–700 of 786
Zhang, R., Wu, S., Jiang, C., Gao, N., Qiu, X., & Zhang, W. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3330166 · Cited by 2
“To address this, Kim et al. [29] proposed a blockchain-based federated learning architecture that incorporates the Proof of Work (PoW) consensus mechanism to replace the central server for aggregation.”
BackgroundOvercoming Trust and Incentive Barriers in Decentralized AI
Singh, A., Lu, C., & Raskar, R. (2024) · IEEE International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi62246.2024.00021 · Cited by 2
“Participants need mechanisms to verify the integrity of uploaded model parameters before aggregation and updates [29], [30].”
Leveraging Blockchain and Coded Computing for Secure Edge Collaborate Learning in Industrial IoT
Chen, Y., Lin, X., Xu, H., Liao, S., Guo, J., & Zou, C. (2024) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn61486.2024.10637571 · Cited by 1
“Kim et al. proposed BlockFL (blockchain FL) [16], which makes use of the PoW (Proof of work) consensus mechanism and monetary incentives to encourage local training of nodes; Sun et al. designed an incentive mechanism [17] for their proposed SCFL model based on contract theory according to the…”
MethodBlockchain-based engine data trustworthy swarm learning management method
Luo, Z., & Zhang, H. (2024) · Blockchain Research and Applications · doi:10.1016/j.bcra.2023.100185 · Cited by 3
Wu, Y., Cheng, H., Guan, L., Liu, P., Chen, F., & Wang, M. (2023) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys60770.2023.00096 · Cited by 4
“To facilitate more active participation, incentive mechanisms [14] [15] [16] have been proposed in FL, which reward clients based on the accuracy improvements of their local models.”
MethodA Comprehensive Survey on Blockchained Federated Learning System and Challenges
Agrawal, N., Mishra, D. K., & Agrawal, S. (2023) · IEEE International Conference on ICT in Business Industry & Government (ICTBIG) · doi:10.1109/ictbig59752.2023.10456007 · Cited by 2
“This facilitates the identification of malevolent endpoints and produces quicker, more performant models [11].”
BackgroundBoosting Classification Tasks with Federated Learning: Concepts, Experiments and Perspectives
Hu, Y., & Chaddad, A. (2023) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe60311.2023.00031 · Cited by 2
“In [79], they proposed the classical cross-device Blockchain FL model, in which local nodes first calculate the initial model and then update the global model based on other information from the model parameters in the new block, which must be verified by miners on the blockchain using a consensus…”
MethodRETRACTED ARTICLE: Blockchain managed federated learning for a secure IoT framework
Chai, J., Li, J., Wei, M., & Zhu, C. (2023) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-023-02311-x · Cited by 4
“To be more specific, Bao et al. [12], Kim et al. [13], and Pokhrel et al. [14] all suggest designs that, if implemented, would make it feasible to carry out FL in a manner that is truly distributed.”
RetractedMulti-dimensional Data Quick Query for Blockchain-Based Federated Learning
Yang, J., Cao, S., Xiangli, P., Li, X., & Zhang, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19211-1_43 · Cited by 4
Research on Blockchain-based Decentralized Federated Learning
Han, B., Liang, Z., Qin, M., Jiang, R., & Dai, W. (2023) · International Conference on Computer Applications Technology · doi:10.1109/ccat59108.2023.00012 · Cited by 3
“The training process involves a central server, also known as a parameter server, and multiple device nodes [11].”
MethodTrustworthy Anti-Collusion Federated Learning Scheme Optimized by Game Theory
Li, Q., Zhou, Q., Li, M., & Wang, Z. (2023) · Electronics · doi:10.3390/electronics12183867 · Cited by 3
Blockchain-based Optimized Client Selection and Privacy Preserved Framework for Federated Learning
Qammar, A., Naouri, A., Ding, J.-G., & Ning, H. (2023) · arXiv.org · doi:10.48550/arxiv.2308.04442 · Cited by 2
“Kim et al. [27], presented the blockchain-enabled federated learning as BlockFL to coordinate the model learning process in a decentralized manner.”
BackgroundZeng, G., Zhang, R., Gao, N., Wu, S., Jiang, C., & Jing, X. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278723 · Cited by 5
“Kim et al. [13] proposes a blockchain federated learning architecture that incorporates the POW (Proof of Work) consensus mechanism to replace the central server for aggregation.”
BackgroundAn Efficient Consensus Algorithm for Blockchain-Based Federated Learning
Kalita, K. P., Boro, D., & Bhattacharyya, D. K. (2023) · International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC) · doi:10.1109/isacc56298.2023.10083761 · Cited by 5
“The authors designed a collaborative architecture in [13], where incentives are provided for mining blocks with PoW and sharing data samples.”
BackgroundRobust privacy‐preserving federated learning framework for IoT devices
Han, Z., Zhou, L. Q., Ge, C., Li, J., & Liu, Z. (2022) · International Journal of Intelligent Systems · doi:10.1002/int.22993 · Cited by 3
“In addition, blockchain ‐ based methods 37 – 39 are also promising and can provide a high ‐ security level, yet the overheads of blockchain ‐ based methods are too heavy for the end devices in resource ‐ constrained environments such as LPWAN.”
DeFTA: A Plug-and-Play Decentralized Replacement for FedAvg
Zhou, Y.-H., Shi, M.-J., Tian, Y., Ye, Q., & Lv, J.-C. (2022) · arXiv.org · doi:10.48550/arxiv.2204.02632 · Cited by 2
“Consequently, several works [17, 18, 19, 20] had replaced the default worker-server architecture in centralized FL in a peer-to-peer (p2p) manner [21] for better scalability and ownership [9].”
InfluentialImproving Security and Fairness in Federated Learning Systems
Short, A. R., Orfanoudakis, T., & Leligou, H. C. (2021) · International Journal of Network Security & Its Applications · doi:10.5121/ijnsa.2021.13604 · Cited by 3
“H. Kim et al [15] have proposed a solution (BlockFL), where a blockchain network is used instead of a central server to facilitate sharing of model updates from client devices.”
BackgroundKaur, U., & Shalu, S. (2021) · Wiley eBooks · doi:10.1002/9781119785873.ch16 · Cited by 4
DecFL: An Ubiquitous Decentralized Model Training Protocol and Framework Empowered by Blockchain
Morsbach, F., & Salman Zubair, T. O. O. R. (2021) · ACM International Symposium on Blockchain and Secure Critical Infrastructure (BSCI) · doi:10.1145/3457337.3457842 · Cited by 2
“DeepChain [44], FLchain [29] and BlockFL [21] are prominent efforts to address the challenges related to federated model train-”
BackgroundConfined Gradient Descent: Privacy-preserving Optimization for Federated LearningPreprint
Zhang, Y., Bai, G., Li, X., Nepal, ., & Ko, R. K. L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.13050 · Cited by 4
Scalable Private P2P network for distributed and Hierarchical Machine Learning in VANETs
Jeon, J. M., & Hong, C. S. (2021) · International Conference on Information Networking · doi:10.1109/icoin50884.2021.9333988 · Cited by 2
“[4] [5] use the blockchain technology approach, but it is computation, complexity is high.”
MethodFair and autonomous sharing of federate learning models in mobile Internet of ThingsPreprint
Hao, X., Ren, W., Xiong, R., Zheng, X., Zhu, T., & Xiong, N. N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.10650 · Cited by 3
“Existing work [26], [27], [28], [29] based on blockchain do not meet the requirements: (a) no trusted third parties, (b) fairness, and (c) publicly verifiable at the same time.”
BackgroundStudy of Efficacious use of Blockchain in 6G Technology-Path for the Future
Voleti, R., & Noida, K. I. G. (2020) · International Journal of Engineering Research and · doi:10.17577/ijertv9is060707 · Cited by 3
“[54] conferred a Distributed Denial-of-Service prevention structure by the assistance of blockchain.”
BackgroundChandrasekaran, G., Kumar, A., Subramaniam, K., Sunil, N., & Challa, R. (2024) · IEEE Access · doi:10.1109/access.2024.3429631 · Cited by 3
“Kim et al. [16] integrate blockchain with FL, where each node represents a single user, necessitating model averaging after all transactions, which can be time-consuming.”
BackgroundLai, W., & Zheng, Y. (2023) · Electronic Research Archive · doi:10.3934/era.2023255 · Cited by 2
“In the literature [24], DNNs were first applied to ASR systems for English in combination with HMMs, and subsequently, recurrent neural networks have all been used to mine more and richer contextual information and thus build more powerful acoustic models for English; and DNN-based ASR systems for English have reached…”
MethodDecentralized Heterogeneous Federal Distillation Learning Based on Blockchain
Zhu, H. G., Gao, L., Sha, Y., Xiang, N., Wu, Y., & Han, S. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.040731 · Cited by 3
“Reference [17] designed a blockchain-based FL architecture that includes multiple mining machines, using blockchains to coordinate f FL tasks and store global models.”
MethodBlockchain Empowered Federated Learning for Medical Data Sharing Model
Wang, Z., Yan, B., & Yao, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86137-7_57 · Cited by 4
Joint Client Scheduling and Resource Allocation Under Channel Uncertainty in Federated Learning
Wadu, M. M., Samarakoon, S., & Bennis, M. (2021) · IEEE Transactions on Communications · doi:10.1109/tcomm.2021.3088528 · Cited by 2
Self-citationEnergy-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
Leveraging federated learning for smart grids: A comprehensive survey
Husnoo, M. A., Anwar, A., & Rahman, M. A. (2026) · Cyber-Physical Energy Systems · doi:10.1016/j.cpes.2026.07.002 · Cited by 1
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
“Kim et al. [36] proposed a blockchain-based FL architecture called BlockFL, which utilizes blockchain for the exchange and verification of local models from mobile devices, enabling machine learning without the need for coordination by a central device.”
Vinita, L. J., & Vetriselvi, V. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1861374 · Cited by 1
“Traditional methods such 10.3389/frai.2026.1861374 as differential privacy (Moya Osorio et al., 2022) and blockchain-enhanced federated learning (FL) (Kim et al., 2020) have been employed, while secure aggregation addresses inference risks (Sumitra and Shenoy, 2023).”
InfluentialSecure Decentralized Federated Learning via Gossip and Virtual VotingPreprint
Taherpour, A., & Wang, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.08651
“A second line of work introduces distributed ledgers [24], [25] into FL. Blockchain-assisted FL systems use tamper-evident records, smart contracts, or consensus mechanisms to reduce reliance on a trusted coordinator [26]–[32].”
Blockchain-Driven Federated Learning for Secure Industrial Predictive Maintenance
Hossain, M. I., Bakchi, N., Hossain, M. I., Das, S., & Ahmed, M. F. (2026) · International Journal of Innovative Science and Research Technology (IJISRT) · doi:10.38124/ijisrt/26jun1585 · Cited by 3
“However, many existing solutions are complex because they use expensive consensus mechanisms, store large amounts of data on-chain, or rely on custom datasets that are difficult to reproduce [9], [15], [16].”
Ram, A., & Chakraborty, S. K. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112360
Bayan, T., Mukhambetiyar, B., Boranbayev, A., & YAZICI, A. (2026) · Data in Brief · doi:10.1016/j.dib.2026.113111 · Cited by 1
“Blockchain-based auditing adds a tamper-evident record of model updates and aggregation rounds [ 6 ], while IPFS provides efficient off-chain storage for model artifacts.”
Matheen Fathima, G., & L, S. (2026) · International Journal of Computer Networks And Applications · doi:10.22247/ijcna/2026/26 · Cited by 1
Sangheethaa, S., Korath, A., & Menon, G. A. (2026) · Information · doi:10.3390/info17050499 · Cited by 2
Zhu, L., Zhao, B., & Peng, R. (2026) · Electronics · doi:10.3390/electronics15081572 · Cited by 4
“Subsequent research shifted to evaluation models based on verifiable statements [73,79], enhancing fairness through immutable behavior evidence recorded on the chain, but it placed higher requirements on the storage space on the chain.”
A novel approach for fair incentive social physical data based on blockchain-federated learning
Mohamed, H. G., Tran-Huy, H., Hoang-Thu, T., Qaddara, I., Choi, B. J., Alshehri, A. H., Ahad, I., & Liu, H. (2026) · Frontiers in Physics · doi:10.3389/fphy.2026.1778336 · Cited by 1
Atmoko, R. A., Pramono, S. H., Purnomo, M. F. E., Mudjirahardjo, P., Rohmatillah, M., & Avian, C. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.15817 · Cited by 3
“Complementary research on blockchain integration provides decentralized coordination and tamper-proof audit trails [49-54].”
What will be the next step of LLMs in TCM? A narrative review
Chen, S., Zhong, R., Zhang, W., Li, Z., Su, Y., Gao, L., & Hu, K. (2026) · Science of Traditional Chinese Medicine · doi:10.1097/st9.0000000000000109 · Cited by 1
Muazu, T., & Mao, Y. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112161 · Cited by 2
Robust federated learning through decentralized adaptive oracle consensus
Li, P., & Grenn, M. W. (2026) · Discover Computing · doi:10.1007/s10791-026-09986-y
Yune, E., & Balan, M. (2026) · International Conference on Consumer Electronics · doi:10.1109/icce67443.2026.11449597
“Blockchain-backed decentralized FL (DeFL) introduces immutable logging and incentives [6], [7], but on-chain aggregation is costly [8], self-reports are unverifiable, and fairness under non-IID data is often ignored [9].”
EBFL: An Efficient Blockchain Framework for Federated Learning Services
Yin, Z., Wang, H., Liu, C., Ding, Y., Li, K., & Li, K. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3646060 · Cited by 1
“FedAvg is a classic FL method, while TBFL is a synchronous scheme that replaces the central server with a blockchain system [5].”
InfluentialIncentive mechanism design in blockchain-based hierarchical federated learning over edge clouds
Liu, X., Liu, J., Wei, X., & Wang, Y. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112039 · Cited by 1
Controlled Self-Recovery of the Aggregator in Federated Learning Using RAFT Protocol
Dautov, R., & Husom, E. J. (2025) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3785470 · Cited by 1
“While such models improve robustness, they also introduce added complexity and overhead, particularly in large-scale or resource-constrained deployments.”
LPV-FL: A Lightweight Privacy-Preserving and Verifiable Federated Learning Scheme
Lei, X., Wang, S., & Fan, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3584084 · Cited by 3
“One of the earliest such efforts was proposed by Kim et al. [20], who designed a blockchain-based FL architecture where smart contracts replace the server, coordinating model updates and providing incentives and verification.”
Enhancing Privacy and Accuracy in Federated Learning Via Local Model Ensemble and Data Shuffling
Li, Y., Li, Z., Zhang, Y., Hao, C., & Xu, G. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11400906
“Chain-PPFL leverages blockchain technology to ensure the integrity and immutability of model updates, thereby enhancing the overall system security[10].”
Wang, Y., Yang, T., & Xiong, C. (2025) · Expert Systems · doi:10.1111/exsy.70166 · Cited by 1
Zhang, Z., Huang, X., Li, C., Li, A.-H., & Xiao, L.-Q. (2025) · China Communications · doi:10.23919/jcc.fa.2023-0496.202511 · Cited by 1
“In traditional public blockchain systems, several transactions need to be bundled into a block, and any missed transactions must wait for the next block, with all transactions in a block needing to pass validation to be effective [7].”
Enhancing Split Learning with Sharded and Blockchain-Enabled SplitFed Approaches
Sokhankhosh, A., Hassan, K., & Rouhani, S. (2025) · IEEE International Conference on Blockchain (Blockchain) · doi:10.1109/blockchain67634.2025.00033 · Cited by 1
“Kim et al. [21] introduced the first blockchain-enabled federated learning framework called BlockFL.”
Blockchain-Secured Federated Learning for Energy Forecasting in Steel Manufacturing
Plabon, N. S., Emon, A. P., Munna, M. S., Dey, J., & Barua, I. J. (2025) · IEEE Region Humanitarian Technology Conference · doi:10.1109/r10-htc63995.2025.11394100
“Recent applications in energy systems, such as the Brooklyn Microgrid project, have demonstrated blockchain's effectiveness for secure energy trading between untrusted parties [7].”
FedBGS: A Blockchain Approach to Segment Gossip Learning in Decentralized Systems
Turazza, F., Pietri, M., Picone, M., & Mamei, M. (2025) · IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW) · doi:10.1109/icdcsw63273.2025.00136 · Cited by 3
“Frame-works such as FLchain [17], BFLC [18], and BlockFL [19] use blockchain to ensure full decentralization in federated learning, providing participants with complete transparency over aggregation operations and the overall system context.”
Liu, P., He, Q., Sen, L., Chen, Y., & Liu, A. (2025) · Computer Communications · doi:10.1016/j.comcom.2025.108196 · Cited by 2
Data-Driven Incentive Mechanisms for Federated Learning in Vehicular Networks
Fathi, F., Montazeri, M., Araabi, B. N., Du, H., Niyato, D. T., & Kebriaei, H. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3547866 · Cited by 1
“However, these studies often assume that all data owners willingly participate in FL [19], a premise that is unrealistic given the resource demands placed on data owners.”
Bhattacharjee, P. P., Koley, C., & Chatterjee, S. (2025) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc66714.2025.11135189 · Cited by 1
“In the execution of BFL, the process is initially contrasted with traditional FL, where a central server aggregates model parameters and updates a global model [31], as shown in Figure 3, Part a .”
Hua, X., Chen, J., Cai, Z., Zhang, L., Liao, G., & Yang, C. (2025) · International Conference on Sensor-Cloud and Edge Computing System (SCECS) · doi:10.1109/scecs65243.2025.11065050 · Cited by 2
“…against four baselines: (1) Fe-dAvg [1], a synchronous federated learning standard; (2) FedAsync [6], an asynchronous method with staleness-aware weighting; (3) FedBuff [8], a buffered asynchronous approach; and (4) BlockFL [32], a blockchain-based framework without dynamic staleness control.”
Li, Y., Xu, Z., Zhou, Z., Wang, Y., Zhang, L., & Crowcroft, J. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3667834 · Cited by 1
“Some recent works have proposed many applications of wireless distributed consensus and analyzed the system performance [5], [6], [8], [16], [27], [28], [29], [30].”
BLOCK CHAIN-ENABLED DEEP LEARNING FRAMEWORK FOR CYBERSECURITY AND SECURE IOT DATA ANALYTICS
Lenka, S., Bajpai, S., Tiwari, V. K., & Kanathey, K. (2024) · Cuestiones de Fisioterapia · doi:10.48047/rw0z6h06 · Cited by 6
Decentralization and Federated Approach for Personal Data Protection and Privacy Control
Singh, S., Verma, S. B., Gupta, B. K., & Agrawal, A. (2024) · Journal of Information assurance and security · doi:10.2478/ias-2024-0014 · Cited by 3
“Federated learning is an example of this approach, where machine learning models are trained across multiple distributed devices without the need to transfer raw data [15-17].”
Kuru, K., & Kuru, K. (2024) · International Conference on Blockchain Computing and Applications (BCCA) · doi:10.1109/bcca62388.2024.10844420 · Cited by 12
“…(BlockFL) mechanism, enabling on-device ML without any centralised, training data or coordination by utilising a consensus mechanism is proposed in [29] to generate local models on mobile devices by exchanging and verifying the parameter updates via blockchain to avoid the aforementioned concerns.”
Securing Data Privacy in the Food Supply Chain Using Integrated BC-FL Technology
Pandey, P., & Jeberson, K. (2024) · Journal of The Institution of Engineers (India) Series B · doi:10.1007/s40031-024-01133-9 · Cited by 2
“An on-device FL-BC architecture (BlockFL) was proposed by [10] which considers the robustness, scalability, latency, eliminates the centralized coordination, and minimizes the need of global learning model.”
LFL-COBC:Lightweight Federated Learning On Blockchain-based Device Contribution Allocation
Li, Q., Sun, Y., & Xi, N. (2024) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana63151.2024.00008 · Cited by 1
“Hyesung Kim et al. [14] analyzed the end-to-end delay model of the system and combined the factors that have a significant impact on the efficiency of each client to carry out the study, paving the way for us to design the blockchain reward mechanism.”
Two-tier Multi-zone Consensus: Enable Intelligence Sharing for AIoT with Enhanced Security
Liu, W., Cao, B., & Peng, M. (2024) · IEEE Annual Congress on Artificial Intelligence of Things (AIoT) · doi:10.1109/aiot63253.2024.00052
Wu, G., Liu, F., Li, S., Song, Q., & Tang, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3355175 · Cited by 4
“This can lead to problems of producing extensive communication rounds when dealing with practical Non-IID data sets [16].”
BackgroundPrivacy-Preserving Data Sharing in IoV: A Federated Learning and Blockchain-Based Approach
Xia, Z., Sun, J., & Tan, J. (2024) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops59551.2024.10615878 · Cited by 4
“Additionally, an article [10] proposed a blockchain-infused federated learning framework designed to safeguard learning parameter security.”
BackgroundSecure Data Sharing Method Based on Federated Learning in IoVs
Fan, S., & Xue, J.-W. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10622887 · Cited by 2
“Kim et al. proposed a reward proportional to the size of the training sample while exchanging and validating local models so that more users participate contributing to more training samples [12] .”
BackgroundMethodSustainable Spectrum Crowdsensing
Zeng, Y., Liu, B., Li, Y., Giustiniano, D., & Banerjee, S. (2024) · IEEE International Symposium on Dynamic Spectrum Access Networks · doi:10.1109/dyspan60163.2024.10632809 · Cited by 1
“Individual reward : Previous work on generalized blockchain and federated learning [8] utilizes a reward mechanism that is proportional only to the number of data records each device contributes.”
Incentive Mechanism of Blockchain-Based Reverse Auction for Federated Learning
Cui, B., & Dang, L. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580195 · Cited by 2
“Research [10] [11] [12] has proposed the use of blockchain to design FL incentives.”
BackgroundMuhdi, A., Yuslam, Y., Ngarifillaili, N., Iqbal, A., & Purnama, Y. (2024) · Journal Neosantara Hybrid Learning · doi:10.55849/jnhl.v2i1.746 · Cited by 2
“(Kim et al., 2020).”
Li, S., Liu, M., & Chen, M. (2024) · arXiv.org · doi:10.48550/arxiv.2406.06477 · Cited by 1
“Recent works have proposed to implement FL over blockchains, especially to counter security threats from malicious server (see, e.g., [24,29,33,34,39,47,56]).”
BackgroundA Research and Analysis of Blockchain Federated Learning
Meng, L., Guo, Y., Song, S., & Cui, C. (2023) · IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE) · doi:10.1109/iceace60673.2023.10442645 · Cited by 2
“In [13], the authors conducted an analysis of the latency induced by the blockchain network in BFL and investigated the end-to-end learning completion delay in BFL.”
BackgroundMethodHiFlow3: a hierarchical Web3-based federated learning framework
Kurada, V. R., & Baruah, P. K. (2025) · International Journal of Computers and Applications · doi:10.1080/1206212x.2025.2580469 · Cited by 1
“FL has since found broad applicability across domains, notably in sensitive fields such as health care and disaster response.”
Trustworthy Federated Learning via Decentralized Consensus Under Communication Constraints
Ye, W., An, X., Yan, X., & Carle, G. (2023) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps58843.2023.10464450 · Cited by 1
“One common approach is to leverage DLT as a platform for model storage, packaging the trained local models into blocks [11].”
MethodSecure Decentralized Learning with Incentives on UTXO-based Blockchains
Lunardon, L. (2023) · IEEE International Conference on Omni-layer Intelligent Systems (COINS) · doi:10.1109/coins57856.2023.10189235 · Cited by 1
Towards Collaborative Privacy-preserving Machine Learning on Private Blockchain
Drungilas, V., Vaičiukynas, E., & Čeponienė, L. (2023) · Iberian Conference on Information Systems and Technologies (CISTI) · doi:10.23919/cisti58278.2023.10211561 · Cited by 1
“Research presenting combinations of blockchain, and ML technologies could be divided into two categories: research that introduces novel blockchain network architectures [8] or research that utilises existing technology [7].”
BackgroundCCFL: Communication-Efficient Cross-Cluster Blockchain-Based Federated Learning
Gao, Z., Song, Y., Lin, Y., Zhang, L., & Yang, Y. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10118958 · Cited by 1
“They focused on system design [8], algorithm optimization [9], security protection [2], or incentive mechanisms [10] of BFL.”
BackgroundMalicious Models-based Federated Learning in Fog Computing Networks
Huang, X., Ren, Y., He, Y., & Chen, Q. (2022) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp55476.2022.10039266 · Cited by 1
“In [4], FL was enabled in the blockchain framework, which could realize the secure verification, FL model storage and optimize transmission delay.”
MethodOptimization of Suzhou Garden Infrastructure Layout Based on Federal Learning
Li, M. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/6076453 · Cited by 2
Marvel DC: A Blockchain-Based Decentralized and Incentive-Compatible Distributed Computing Protocol
McMenamin, C., & Daza, V. (2022) · Social Science Research Network · doi:10.48550/arxiv.2207.14011 · Cited by 1
“Blockchain-based DC protocols [16, 1, 20, 19, 13, 27, 26] have been wellstudied also.”
BackgroundLeveraging Centric Data Federated Learning Using Blockchain For Integrity AssurancePreprint
Chaabene, R. B., Amayed, D., & Cheriet, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.04731 · Cited by 3
“In the case of our framework, we have a model which is stored in a decentralized environment which is the public blockchain(Kim et al. 2020)İt is accessible by all the network participants.”
Survey on challenges of federated learning in edge computing scenarios
Zhang, Y., Zhai, R., Wang, Y., & Wang, X. (2022) · Other Conferences · doi:10.1117/12.2629118 · Cited by 1
Blockchain-inspired Distributed Trust in a Smart Vehicular Network System
Samal, T., & Dutta, R. (2021) · IEEE International Conference on Advanced Networks and Telecommunications Systems · doi:10.1109/ants52808.2021.9936927 · Cited by 1
“In [6], an on-device machine learning is proposed as a solution for high reliability for wireless systems, wherein each device stores a machine learning model and is thereby capable of making decisions, when it loses connectivity.”
BackgroundLatency Analysis of Consortium Blockchained Federated LearningPreprint
Ren, P., & Yan, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.04087 · Cited by 1
“And the global model update latency T ` global,0 in Step 6 can be given as T ` global,0 = δmNB/fc [5], where δm is the size of a local model update tx.”
InfluentialCollaborative learning with taboos for machine learning methods in big data problems
Połap, D., & Woźniak, M. (2020) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci47803.2020.9308296 · Cited by 2
“One of solutions is using blockchain proposed in [11], where small data can be stored in blocks based on peer-to-peer transfer model.”
MethodYoo, S., Kim, D.-Y., & Kim, D.-Y. (2026) · IEEE Access · doi:10.1109/access.2026.3671712 · Cited by 2
“A distributed ledger provides immutable and transparent records of all agents’ activities and learning outcomes, ensuring that participants’ actions can be verified at any time [12], [13].”
Yarham, S., Behjati, M., & Alobaidy, H. A. H. (2026) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2026.3690680 · Cited by 1
“At the server level, blockchain-based logging improves transparency and resilience to server compromise [73], [74], [77].”
Wang, Z., Hisada, M., & Abdallah, A. B. (2024) · IEEE Access · doi:10.1109/access.2024.3359272 · Cited by 3
“Aiming to address the potential risk of privacy-sensitive pattern discovery through model updates in collaborative edge learning, blockchain has emerged as an emerging paradigm that ensures high-quality learning [14], [15].”
BackgroundDefending Against Malicious Behaviors in Federated Learning with Blockchain
Dong, N.-Q., Wang, Z.-P., Sun, J.-H., Kampffmeyer, M. C., Wen, Y., Zhang, S., Knottenbelt, W. J., & Xing, E. (2023) · arXiv.org · doi:10.48550/arxiv.2307.00543 · Cited by 1
“Current blockchain-based FL designs [8], [35], [36], [37], [38] have been broadly used in diverse fields [39], [40], [41].”
BackgroundHow Much Does It Cost to Train a Machine Learning Model over Distributed Data Sources?
Guerra, E., Wilhelmi, F., Miozzo, M., & Dini, P. (2022) · arXiv.org · doi:10.48550/arxiv.2209.07124 · Cited by 1
“Another prominent solution to decentralize FL is blockchain-enabled FL [31], [32], [33].”
BackgroundMethodOpenFed: An Open-Source Security and Privacy Guaranteed Federated Learning FrameworkPreprint
Chen, D.-S. (2021) · arXiv.org · doi:10.48550/arxiv.2109.07852 · Cited by 1
“There has been research work demonstrating vulnerabilities in FL, for example, it has been shown that the content of training data can be inferred (to some degree) through the exposed gradients [43, 44].”
BackgroundLin, J., Zhang, L., Tu, J., Ma, W., & Guo, R. (2026) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2026.104696
Zhong, Z., Li, D., Miao, P., Li, H., & Fan, L. (2026) · Blockchain · doi:10.55092/blockchain20260009
“Distributed records have served coordination and auditing in blockchain-enabled FL [24]; surveys examine the associated trust, incentive, and decentralization questions [25].”
Torstensson, O., Prokopovych-Tkachenko, D., Desiatko, A., Babenko, K., Tyshchenko, D., & Франчук, Т. (2026) · Future Internet · doi:10.3390/fi18110594
Zhang, J., Lingfan, T., Gong, J., Lu, S., & Xu, B. (2026) · Information Sciences · doi:10.1016/j.ins.2026.124400
Feng, L.-B., Xie, J.-L., Liu, X.-R., He, Z.-L., Zhang, J.-X., Yu, Y.-M., & Li, K.-Q. (2026) · IEEE transactions on consumer electronics · doi:10.1109/tce.2026.3699680
AuditFL: A Contract-Backed Clearing Layer for Open Federated LearningPreprint
Balla, A., & Lalis, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.41278
“BlockFL studies the latency consequences of replacing a central FL coordinator with block generation [8].”
Adaptive multi-metric aggregation for cost-efficient and fair blockchain-federated learning
Sharma, R., Sahay, S., Sahu, Y., Vishwakarma, G., & Bhargava, A. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07561-y
“When blockchain is used to provide auditability and tamper-evidence, a design attracting sustained interest for federated training [23, 25], naive full-parameteron-chainstorageincursgascoststhatgrowlinearly with model size.”
Metadata
- Authors
- Kim, H., Park, J., Bennis, M., & Kim, S.-L.
- Affiliations
- Yonsei University (KR)
- University of Oulu (FI)
- Venue
- IEEE Communications Letters
- Published
- 2020-06
- Volume
- 24
- Issue
- 6
- Pages
- 1279-1283
- ISSN
- 1089-7798 (ISSN-L)
- 1558-2558
- 2373-7891
- OpenAlex
- W2951832089
- Cited by
- 887
- References
- 16
- Citations by year
- 2026: 81 · 2025: 113 · 2024: 159 · 2023: 173 · 2022: 147 · 2021: 130 · 2020: 73
- FWCI
- 111.77
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Communications Letters (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- Institute of Information & Communications Technology Planning & Evaluation (IITP) grant
- Korea Government (MSIT) (Virtual Presence in Moving Objects through 5G), Basic Science Research Foundation of Korea (NRF) grant (2018-0-00170)
- Ministry of Science and ICT (NRF-2017R1A2A2A05069810)
- Mobile Edge Intelligence at Scale (ELLIS) Project at the University of Oulu
- Topics
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology in Education and Learning
- Keywords
- blockchain, on-device learning, consensus algorithms, decentralized learning
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.