The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Privacy-Preserving Byzantine-Robust Federated Learning via Blockchain Systems
Open accessAbstract
Federated learning enables clients to train a machine learning model jointly without sharing their local data. However, due to the centrality of federated learning framework and the untrustworthiness of clients, traditional federated learning solutions are vulnerable to poisoning attacks from malicious clients and servers. In this paper, we aim to mitigate the impact of the central server and malicious clients by designing a Privacy-preserving Byzantine-robust Federated Learning (PBFL) scheme based on blockchain. Specifically, we use cosine similarity to judge the malicious gradients uploaded by malicious clients. Then, we adopt fully homomorphic encryption to provide secure aggregation. Finally, we use blockchain system to facilitate transparent processes and implementation of regulations. Our formal analysis proves that our scheme achieves convergence and provides privacy protection. Our extensive experiments on different datasets demonstrate that our scheme is robust and efficient. Even if the root dataset is small, our scheme can achieve the same efficiency as FedSGD.
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
“The use of secure robust aggregation is currently recognized as an effective means for defending against Byzantine attacks (Li et al. 2023d;Miao et al. 2022;Wan et al. 2022).”
From Survey: federated learning data security and privacy-preserving in edge-Internet of Things (2024) · cites this paper as Miao et al. 2022
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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
Public-Key Cryptosystems Based on Composite Degree Residuosity Classes
Paillier, P. (2007) · Lecture Notes in Computer Science · doi:10.1007/3-540-48910-x_16 · Cited by 7,250
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
Practical 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
Differential Privacy: A Survey of Results
Dwork, C. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79228-4_1 · Cited by 3,542
Deep Learning: Methods and Applications
Deng, L., & Yu, D. (2014) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000039 · Cited by 3,480
Protocols for secure computations
Yao, A. C. (1982) · 23rd Annual Symposium on Foundations of Computer Science (sfcs 1982) · doi:10.1109/sfcs.1982.38 · Cited by 3,306
Large Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · Cited by 3,202
Homomorphic Encryption for Arithmetic of Approximate Numbers
Cheon, J. H., Kim, A., Kim, M., & Song, Y. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-70694-8_15 · Cited by 2,522
Research works printed but not linked: 1
- 10.1109/MNET.011.2000263 · DOI · Paper page
Cited by
Sorted by citations
Items 201–300 of 301
Resisting against targeted poisoning attacks in lightweight privacy preserving federated learning
Zhang, H., Xie, H., & Lv, J. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07829-z · Cited by 2
“To address both types of threats, some works [23, 24] have proposed combining HE with statistical knowledge.”
A Truthful Incentive Scheme Based on Data Forgetting Game for Federated Unlearning
Xie, L., Su, Z., Wang, Y., Tao, J., & Lin, J. (2025) · IEEE International Conference on Privacy Computing and Data Security (PCDS) · doi:10.1109/pcds65695.2025.00030 · Cited by 2
“In this context, based on the cosine similarity-based algorithm in [12], [13], by comparing (cid:2) (cid:2) 1 i and ki , the FL server can estimate the remaining data size for client i .”
DRIFT: DCT-based robust and intelligent federated learning with trusted privacy
Dong, Q., Bai, Y., Su, M., Gao, Y., & Fu, A. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131697 · Cited by 1
FLClustering: A Fair and Robust Federated Learning Approach in Heterogeneous Environments
Lin, L., Shen, W., Song, C.-H., & Ma, S. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3602647 · Cited by 1
“…mean, median, gradient clipping and normalization [22], [25], and distance metrics methods such as FLTrust [35] and Privacy-preserving Byzantine-robust Feder-ated Learning [26], which use cosine similarity to determine the similarity between participant model updates and global model updates.”
Enhancing Federated Learning in Edge Computing With Secure Aggregation and Dynamic Verification
Li, M., Tian, Y., Zhang, J., Xiong, J., Cui, X., & Ma, J. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3625654 · Cited by 1
Hossain, M. S., Rahman, M. M., & Mahmud, M. (2025) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2025.068779 · Cited by 1
Wu, Y., Cheng, H., Liu, X., Xu, Y., Chen, F., Zhang, X., & Wang, M. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3626847 · Cited by 2
“Duetotheuntrustworthinessofclientsandthecentralityof FLarchitectures,conventionalFLapproachesarevulnerableto poisoningattacksfrommaliciousclientsandprivacydisclosure fromtheserver[5].”
Cerflan: Communication-Efficient norm bounding for robust federated learning
Li, S., Wei, X., Wang, H., Su, Y., & Susilo, W. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103909 · Cited by 1
SA-FL: Secure Aggregation Scheme in Federated Learning Against Poisoning Attacks
Chang, Y., Chen, Q., Luan, T. H., & Su, Z. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3656284 · Cited by 1
“This is a common and practical assumption in secure aggregation and Byzantine-resilient learning [31], [32], as meaningful aggregation requires a majority of honest participants.”
A Robust Privacy-Preserving Federated Learning Method Against Poisoning Attacks on Non-IID Data
Fang, C., Chang, D., Li, Y., Yang, F., Liu, Y., & Ma, B. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3658384 · Cited by 1
“In order to protect data privacy without causing accuracy loss, Miao et al. [34] adopted fully homomorphic encryption to realize secure aggregation and cosine similarity to judge poisoning gradients, during which the intermediate results and model updates are recorded on the blockchain to ensure…”
BDFL: a blockchain-based decentralized federated learning security framework
Shi, K., Xue, T., Wang, J., Wu, Y., & Guo, H. (2026) · Multimedia Systems · doi:10.1007/s00530-025-02148-y · Cited by 1
“Miao et al. [28] pro-pose a scheme that uses blockchain to record model parameters and validation logs, employing consensus mechanisms to detect malicious nodes and combining homomorphic encryption to protect data privacy, thus defending against Byzantine attacks while balancing security and…”
Beyond Centralized AI: Blockchain-Enabled Decentralized Learning
Wang, D., Ma, T., Zhu, J., & Duan, H. (2026) · Future Internet · doi:10.3390/fi18020098 · Cited by 1
“There are several other notable blockchain-based federated learning frameworks, including Fantastyc, BlockFLA, PBFL [54–56], etc.”
Privacy-Preserving and Poisoning-Resilient Enhanced Cross-Silo Federated Learning
Zheng, X., Yan, X., Yang, F., Ng, W. W. Y., Li, Y., & Wu, S. (2025) · International Conference on Blockchain Technology and Information Security (ICBCTIS) · doi:10.1109/icbctis66509.2025.11387244 · Cited by 1
“Due to its advantages in privacy protection and resource efficiency, FL is widely applied in domains where data sharing is restricted by legal regulations, such as smart city IoT applications [2] and cross-organization collaborative learning [3].”
Dual-layer grouping consensus for decentralized federated learning
Li, M., Xia, B., Cai, L., & Luo, B. (2026) · The Computer Journal · doi:10.1093/comjnl/bxag030 · Cited by 1
PRFed: Privacy-preserving federated learning to resist poisoning attack
Li, H., Chen, Y., Yang, Y., Dou, H., & Yang, Y. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104397 · Cited by 1
Self-citationNakayiza, H. L., Ahakonye, L. A. C., Kim, D., & Lee, J. M. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3691349 · Cited by 1
“In addition, PBFL [29], which uses cosine similarity to identify malicious gradients, is included as a reference baseline to contextualize performance relative to existing work.”
FedVPN: A Federated Multi-Modal Perception Framework for Multi-UAV in Mountain Search and Rescue
Liu, Q., Zhang, D., & Li, S. (2026) · Electronics · doi:10.3390/electronics15122678 · Cited by 1
Ezzeddine, H., Issa, R., & Abbas, N. (2026) · Journal of Cyber Security Technology · doi:10.1080/23742917.2026.2696259 · Cited by 1
Gouse, S. M., & Burra, V. B. (2023) · International Journal of Reliability Quality and Safety Engineering · doi:10.1142/s0218539323410036 · Cited by 1
Wang, Z., Hisada, M., & Abdallah, A. B. (2024) · IEEE Access · doi:10.1109/access.2024.3359272 · Cited by 1
“Other studies approach this problem through client selection using model similarity [12], [13], which is sensitive to dimensionality and magnitude of model vectors.”
MethodXu, J., Guo, B., Chen, F., Shen, Y. H., Dai, S., & Dai, C. (2023) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom59178.2023.00110 · Cited by 1
“Bagdasaryan et al. [12] introduced a method that involved adding noise to the client's data to prevent malicious participants from reverse-engineering user data through model updates.”
MethodSecure Healthcare Predictive Modeling with Homomorphic Encryption
Shekhu, P., Sethi, S., & Chaudhary, A. (2024) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom61295.2024.10498904 · Cited by 1
FedMSD: Multi-Stage Defense Against Poisoning Attacks in Data Heterogeneous Federated Learning
Zhang, X., Tong, F., & Xing, F. (2024) · International Conference on Artificial Intelligence of Things and Systems (AIoTSys) · doi:10.1109/aiotsys63104.2024.10780671 · Cited by 2
“The authors in [17] proposes FLTrust, an approach that employs the server’s clean root dataset to authenticate the poisoning attack.”
Zhang, Y., Wang, L., Luo, Y., Zhang, K., Yu, L., & Chen, K. (2025) · The Computer Journal · doi:10.1093/comjnl/bxae141 · Cited by 1
Blockchain Based Privacy Preservation and Misbehavior Analysis in Financial Supply Chain
Sumalatha, M. R., Kumar, A., Janardhanan, N., & Abhinash, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-81458-7_14 · Cited by 1
Bokade, S., Sharma, V. K., & Manjre, B. M. (2024) · International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA) · doi:10.1109/icaiqsa64000.2024.10882419 · Cited by 1
“In Table 1, it can be observed that on the Bitcoin dataset, the proposed model gives a higher F1-score, 0.92, than Method [4] at 0.85, Method [9] at 0.83, and Method [18] at 0.78.”
InfluentialResearch Directions for Decentralized Technology Transactions: An Update
Hadi, A., Rahmadika, S., Rahmi, U., Larasati, H. T., & Fajri, B. R. (2025) · Salud Ciencia y Tecnología · doi:10.56294/saludcyt20252161 · Cited by 1
Sameera, K. M., Vinod, P., Rocha, A. D. R., A., R. R. K., & Conti, M. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104275 · Cited by 1
Privacy-Preserving Federated Learning Compatible with Robust AggregatorsPreprint
Alebouyeh, Z., & Bidgoly, A. J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4793556 · Cited by 1
Obscuring Transaction Information in Decentralized P2P Wireless Networks
Hadi, A., Rahmadika, S., Fajri, B. R., Farell, G., Budayawan, K., & Lofandri, W. (2023) · IEEE Access · doi:10.1109/access.2023.3321960
Optimizing Federated Learning Approach: Literature Survey and Open Points
El-Sayed, T., Moustafa, A., El-Rashidy, M. A., & El‐Sayed, A. (2023) · International Conference on Electronic Engineering (ICEEM) · doi:10.1109/iceem58740.2023.10319542
“[41] employs blockchain to enhance transparent procedures and enforce rules.”
MethodLiao, B.-Y., & Chang, J.-W. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-9342-0_5
A Privacy Protecting Mechanism in UAV-MEC Network with Blockchain-Enabled Federated Learning
Zhu, C., Zhu, X., Zhang, Z., & Qin, T. (2023) · International Conference on Communication and Network Security (ICCNS) · doi:10.1145/3638782.3638817
“Differentfromtraditionaldistributedmachine learning,federatedlearningrequiresadecentralizeddistributed systemtoensuretheprivacyandsecurityofbasestations[10], andtocarryouteffectivemachinelearningunderthepremiseof ensuringdatasecurityandexchangeandtrainingefficiency[6].”
Blockchain-based Federated Learning via Model Training
Wang, R., & Wang, J. (2023) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbd-ai62252.2023.00045
“Y. Miao et al. [17] used full homomorphic encryption (CKKS17) to protect local data training and reduce computing and communication overhead.”
BackgroundPrivacy-Preserving Federated Learning Compatible with Robust AggregatorsPreprint
Alebouyeh, Z., & Bidgoly, A. J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4882102
Cai, Y., & Song, W. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5552-3_33
Blockchain Enabled Federated Learning-Based Medical Cyber-Physical System
Basak, S., Kumar, A., & Chatterjee, K. (2024) · International Conference on Electronics, Communication and Signal Processing (ICECSP) · doi:10.1109/icecsp61809.2024.10698609 · Cited by 2
“A blockchain-based Privacy-preserving Byzantine-robust FL is proposed in [10] that is capable of predicting malicious clients, but the computation cost may increase for fully homomorphic encryption.”
BackgroundSecure Federated Distillation Framework for Encrypted Traffic Classification
Teng, L., Feng, Q. B., Zhao, W., Luo, M., & He, D. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9053-1_1
Why Not Model Privacy?: An Efficient and Practical Scheme for Federated Learning Model Security
Wang, S., Bi, R., Tian, Y., & Xiong, J. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-60347-1_33
Byzantine-Robust Federated Learning Based on Blockchain
Song, L., Cai, C., Wei, S., Banerjee, R., Feng, X., & Jiang, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71464-1_39
A backdoor attack defense scheme in federated learning
Jing, Z., & He, J. (2024) · IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · doi:10.1109/iciba62489.2024.10867968
“Inaddition, Miao et al. [19] combined Byzantine defense with secure multi-party computation, using principal component analysis and mean clustering techniques to identify and eliminate abnormal clients, and further strengthened privacy protection through additive secret sharing.”
Euclidean-Based Client Selection in Federated Learning
邬, 淑. (2025) · Modeling and Simulation · doi:10.12677/mos.2025.144366
Federated Learning: An Overview of Attacks and Defense Methods
Sameera, K. M., Arikkat, D. R., Vinod, P., A., R. R. K., Aneez, A., & Conti, M. (2025) · Springer eBooks · doi:10.1007/978-3-031-83157-7_14
Federated Learning Privacy-preserving Scheme Based on DMK-CKKS
Zhao, Y., Li, H., Wang, W., Liu, Y., & Zou, C. (2025) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit65432.2025.11035269
“Since then, more research has focused on applying homomorphic encryption algorithms to federated learning[6-8].”
Self-citationsu, Q., Zhang, G., li, H., & Ge, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5506730
Self-citationA Verifiable Federated Learning Scheme With Privacy-Preserving in MCS
Gu, K., Lei, J., Tan, J., & Li, X. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3627581
“Miao et al. [22] designed a blockchain-based privacy-preserving Byzantine robust FL scheme, which can decrease the influence of central server and malicious clients.”
LiveVal: Real-time and Trajectory-based Data Valuation via Adaptive Reference Points
Xu, J., Wu, Z., Wang, C., & Jia, X. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761138
SEGS: Self-Enforcing Group Signature for Voting Systems
Bao, Z., He, D., Feng, Q., & Luo, M. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3632560
Secure and Trustworthy Federated Learning Framework via Hierarchical Sharding Blockchain
Wei, Z., Wang, J., Zhao, Z., Zhao, Z., & Li, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3639396
“Miao et al. [16] proposed a Byzantine-robust FL framework named PBFL based on blockchain and homomorphic encryption, which actively guides server trust through trusted nodes and uses blockchain to record FL training processes.”
Dual-Key Verifiable Secure Aggregation for Federated Learning via Blockchain
Zhang, Y., Ma, Y., Liu, W., Pang, Y., Wang, Y., & Yuan, H. (2025) · IEEE International Conference on Blockchain (Blockchain) · doi:10.1109/blockchain67634.2025.00032
“Additionally, Additionally, Study [12] through the use of additive homomorphic secret sharing, enhancement of SA was attained which allowed for the processing of aggregated shared data without a need for its reconstruction.”
Secure and Robust Federated Learning Under Dual-Server Architecture in Internet of Things
Liu, S., Ren, J., Meng, R., Yan, X., Miao, Y., Liu, Z., Peng, J., Zou, Y., Wang, Z., Li, H., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3647441
“Therefore, the study of defenses against poisoning attacks within PPFL has attracted increasing attention in recent years [13], [14], [15].”
Self-citationZero-knowledge clustering and selective federated distillation for decentralized federated learning
Chen, S., Pan, S., & Li, X. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.114584
Sutoyo, A. A., Putra, E. H., Gabriella, T., Manuaba, I. B. K., Chen, Y., & Setiawan, F. (2025) · International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM) · doi:10.1109/cenim67940.2025.11325803
“…an FL framework for obesity prediction, leveraging Federated Averaging (FedAvg), a variant of FL that extends FedSGD by allowing each local client to perform multiple rounds of updates on their local dataset before submitting the updated model parameters for aggregation by a central server [20].”
Secure Hierarchical Asynchronous Federated Learning with Shuffle Model and Mask–DP
Chen, Y., Ai, D., & Yan, L. (2026) · Sensors · doi:10.3390/s26020617
“There are three typical privacy protection methods in FL: HE [26,27], DP [18,32,53,54], and SMC [29–31].”
XLedger: A Scalable Data Synchronization Protocol for Multi-chain Weak Consistency Scenarios
Li, D., Liu, X., Ma, L., Xu, H., & Li, K. (2025) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn69125.2025.00039
“Inter-chain data synchronization [1], [2] lays the foundation for building complex multi-chain applications [3], [4], [5] through blockchain interoperability technology [6], [7], [8], [9].”
Zhang, Y., Zhao, W., & Hu, C. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108390
Privacy Preservation and Fair Payment Method Based on Blockchain and Federated Learning
Shen, M., Xiong, X., Hu, D., Xi, X., Cao, W., & Wang, X. (2025) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom67567.2025.11331510
“After local training, each client C j encrypts its updated model W = [ w j [1] , . . . , w j [ ζ ]] using the NIFE scheme with SIMD technology.”
A Scalable and Secure Architecture for Explainable AI in Blockchain-Integrated Analytics Platforms
Syed, A. A., Sambamurthy, P. K., & Mamodiya, U. (2025) · International Conference on Electrical, Electronics, and Computer Science with Advance Power Technologies - A Future Trends (ICE2CPT) · doi:10.1109/ice2cpt66440.2025.11340011
Privacy-Preserving Blockchain-Enabled Vertical Federated Learning with Data Auditing
Li, B., Xu, Z., Zhang, Y., & Wang, H. (2025) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds69199.2025.00019
“Despite extensive research on blockchain-enabled horizontal federated learning (HFL) [9]–[11], few studies have focused on VFL setting.”
LDP-Rep: Lightweight Byzantine-Robust Aggregation for Non-IID Federated Learning
Chen, S., & Wei, Y. (2025) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca67083.2025.11350237
“However, under increased attack intensity, the accuracy of LDP is significantly lower than that of HE [12][13].”
Core-Set Selection Considering Parties Honesty in Vertical Federated Learning
Hong, J., Liu, Y., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5722-6_2
RESA: RLWE-Based Efficient Secure Aggregation For Federated Learning
Wang, Z., Zhang, L., Zhou, H., Kan, H., & Zhang, J. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00338 · Cited by 1
“For example, [20], [21] use Paillier [8] to encrypt gradients and [22], [23] use CKKS [9] to encrypt the gradient.”
Wang, X., Jiang, Y., Pan, G., Luo, Z., Xiao, M., Yang, L., Shi, X., Huo, Y., Li, M., & Zhang, L. (2026) · Scientific Reports · doi:10.1038/s41598-026-38906-9 · Cited by 1
“By innovatively combining CKKS fully homomorphic encryption 35 with the Paillier semi-homomorphic mechanism 36 , this algorithm applies differential encryption levels based on parameter importance and utilizes a random transmission sequence.”
Qi, Q., Lei, Y., Li, Y., Li, H., & Zhou, Q. F. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3661499
“Secondly, current decentralized FL architectures are susceptible to Byzantine attacks [6], [7], [8], [9], where malicious participants can send arbitrary or conflicting information to disrupt the sys-tem.”
Self-citationN.Padmashri, V.V.Karthikeyan, P.Sumathi, Potnuru, S. K., Aswathy, P. B., & V.Baby (2025) · International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT) · doi:10.1109/icerect65215.2025.11379725
RankFL: Robustness and Privacy-Preserving Federated Learning Scheme Against Poisoning Attacks
Chang, Y., Chen, Q., Luan, T. H., & Su, Z. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3672641
Dong, Q., Dai, Z., Gao, Y., Zheng, Y., Fu, A., & Susilo, W. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3674690
“For any w , b w , we have [38] Assumption 2: The gradient of the empirical loss function ∇ L ( x , w ∗ , y ) at the optimal global model w ∗ is bounded.”
Cai, H., Chen, Z., Guo, E., & Wang, X. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-21171-2_21
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
Liu, Y., Jia, L., Yang, X. Y., Li, Z., & Sun, Y. W. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792469
“However, this design suffers from centralized security risks [28, 36] and, as shard numbers increase, frequent global synchronization creates severe performance bottlenecks.”
SecureTensor for federated learning with privacy preservation and communication efficiency
Wu, X., Lou, F., Chen, X., Chen, Y., Lan, T., & Wang, Z. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133832
DDFL: dual defense against poisoning attacks in privacy-preserving federated learning
Guo, C., Tian, M., Li, X., Sun, H., & Jie, Y. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109095
Federated learning for speech and text based depression detection
Gaikwad, P. P., & Venkatesan, M. (2026) · AIP conference proceedings · doi:10.1063/5.0344267
PBSFL: Privacy-Preserving and Byzantine-Resilient for Summoning Federated Learning
Chen, B., Ke, Y., Zhang, W., & Liu, J. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00847-8
“Table 6 shows that PBSFL achieves a time cost comparable to PBFL, and PBSFL(CRT) further reduces decryption and inner product overhead by employing CRT optimization.”
InfluentialZheng, Y., Tian, Y., Zhou, Z., Wang, S., Li, M., & Xiong, J. (2026) · IET Communications · doi:10.1049/cmu2.70173
Trustworthy Multimodal Federated Learning: A Survey of Feasibility, Adversariality, and SecurityPreprint
Yuan, Z., Luo, Y., Deng, G., Chen, S., Jiang, W., Yang, X., Wu, S., Wang, K., Wang, M., Rao, C., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6849573
Privacy-Aware and Scalable Blockchain Solutions in Healthcare: Emerging Directions
Singh, G., & Haroon, D. M. (2026) · Journal of Information assurance and security · doi:10.2478/ias-2026-0003
“This is because researchers often ignore the most important features, like being able to handle a lot of clinical data, working with standards like HL7, FHIR, and DICOM, and using privacy-preserving cryptography that is necessary for compliance with regulations [5].”
Bilateral-verifiable and robust secure aggregation via TEE for asynchronous federated learning
Liu, W., Zhang, Y., Wu, A., Cao, J. P., Wang, Y., & Tian, Y. (2026) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2026.104542
Song, L., Xue, Q., Wang, Z., Ma, H., & Li, Z. (2026) · IET Blockchain · doi:10.1049/blc2.70047
BRPPFL: A Byzantine-Robust and Privacy-Preserving Framework for Cloud–Edge Federated Learning
Zhang, L., Qiancheng, Y., Wuwei, Y., & He, L. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112498
PRBPR: Privacy-Preserving Redactable Blockchain Supporting Policy Hiding and Revocation
He, L., Wang, C., Shen, J., Li, F., Wang, W., & Rodrigues, J. J. P. C. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3707429
“…sharing among mutually untrusted parties, and has found applications across diverse domains, including the Internet of Vehicles [2], [3], [4], federated learning [5], [6], the Internet of Things [7], [8], electronic voting [9], [10], and supply chain [11], [12], among others [13], [14], [15], [16].”
Venturini, J. F. D., Leite, A. E. G., & Hessel, F. P. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-23311-0_8
Byzantine-Resistant Federated Learning Using Reinforced RNN
Rathika, P., Priyadharshini, A., Karthi, V., Elakkiya, G., Praveen, J. J., & Manjith, S. (2026) · International Conference on Computing, Communication and Green Engineering (CCGE) · doi:10.1109/ccge67142.2026.11581834
“The proposed PBFL utilizes a blockchain federative learning paradigm that minimizes the impact of rogue clients and the server of 85%[20].”
SAFL: Enhanced Defense Against Poisoning Attacks in Privacy-Preserving Federated Learning
Lai, H., Chen, J., Wu, G., Liu, X., & Chen, C. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581500
“To address the requirements of PPFL, several schemes such as PBFL [7], ShieldFL [8], RFed [9], SPPFL [10], and PEFL [11] were proposed with distinct technical approaches to enhance security.”
Blockchain-Assisted Privacy-Preserving and Robust Federated Learning in Edge Computing
Shen, X., Xu, C. L., Zhu, L., Liu, H., Sun, L., & Sharif, K. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3710509
“This assumption matches prior privacy-preserving and Byzantine-robust FL systems [11], [25].”
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
“Blockchain is a decentralized distributed ledger that can record transaction information and ensure its integrity and immutability, thus attracting significant attention [21], [22].”
Zhang, T. A., Yang, L., Wang, J., Yuan, F., Zhang, C. L., & Kang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2862-1_13
Chen, S., Zhang, W., Nie, J., Dai, Z., & Mao, Q. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123909
Sharmila, A. H., & Deepanramkumar, P. (2026) · Array · doi:10.1016/j.array.2026.101114
LBSFL: a lightweight robust federated learning method for IoT
Ma, W., Tian, W., Zhao, Q., & Wang, X. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01110-w
“To address this, Liu et al. proposed GTG-Shapley (Liu et al. 2022), which approximates Shapley value computation by reconstructing client gradients and incorporating guided truncation sampling.”
Background of Machine Unlearning
Xu, J., & Jia, X. (2026) · Wireless networks · doi:10.1007/978-3-032-30978-5_2
Khan, M. A., Anis, G., Naz, N. S., Saleem, M. A., Mazhar, T., Farooq, M. S., Lee, S.-W., & Hamam, H. (2026) · International Journal of Energy Research · doi:10.1155/er/1942591
Gu, C., Zhu, K., Hu, D., & Liu, Z. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104731
Self-citationPrivacy-Preserving and Byzantine-Robust Federated Learning With Mean-Constrained Secret Sharing
Zhu, G., Wu, L., & Liu, K. (2026) · IEEE Access · doi:10.1109/access.2026.3729203
“Research shows that malicious servers or participants can infer client identities, reconstruct samples, or extract attributes by analyzing gradients [1], [2].”
Privacy-preserving methodologies against privacy attacks on deep learning: a survey
Ghosh, S., & Mandal, A. K. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02865-4
VERSA: A novel framework for verifiable and secure aggregation in Summoned Federated Learning
Chen, B., Ke, Y., Zhang, W., Xu, C., & Liu, C. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112750
Privacy-Preserving Robust Federated Learning Based on Threshold Homomorphic Encryption
Zhao, Q., Zhoupeng, F., Zhang, M., Qin, B., 秦, 香., & Zhang, B. (2026) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc70295.2026.11680499
“Specifically, ShieldFL [12] and PBFL [13] integrate similarity-based defense into HE-based PPFL, yet both rely on two non-colluding servers to execute interactive secure protocols, incurring substantial communication overhead.”
Shen, F., Liu, Z., Chao, X. U., Liu, Z., Feng, J., & He, Y. (2026) · Information Sciences · doi:10.1016/j.ins.2026.124194
Self-citationRetFL: 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
“Miao et al. (2022) propose PBFL, which integrates blockchain, homomorphic encryption, and Byzantine-robust aggregation.”
PA-CFL: Privacy-Preserving Adaptive Clustered Federated Learning Under Heterogeneous Data
Zhang, T., Wenting, S., Zhang, H., & Zhao, C. (2026) · Mathematics · doi:10.3390/math14203673
Metadata
- Authors
- Miao, Y., Liu, Z., Li, H., Choo, K.-K. R., & Deng, R. H.
- Affiliations
- Xidian University (CN)
- University of Electronic Science and Technology of China (CN)
- The University of Texas at San Antonio (US)
- Singapore Management University (SG)
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2022
- Volume
- 17
- Pages
- 2848-2861
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W4289656845
- Semantic Scholar
- 0070997f3305097cce932a073a09e2bed9c8d406
- Cited by
- 303
- References
- 41
- Citations by year
- 2026: 57 · 2025: 101 · 2024: 97 · 2023: 44 · 2022: 4
- FWCI
- 20.23
- Type
- journal article
- Language
- en
- Open access
- Licence
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion, other-oa)
- Funders
- National Natural Science Foundation of China (62072361, 62125205)
- Key Research and Development Program of Shaanxi (2022GY-019)
- Fundamental Research Funds for the Central Universities (JB211505)
- Henan Key Laboratory of Network Cryptography Technology and the State Key Laboratory of Mathematical Engineering and Advanced Computing (LNCT2020-A06)
- Cloud Technology Endowed Professorship
- 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, privacy preservation, Byzantine robustness, blockchain, poisoning attacks, malicious clients, malicious server, cosine similarity, fully homomorphic encryption, secure aggregation, convergence analysis
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
