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 101–200 of 301
DBFL: Dynamic Byzantine-Robust Privacy Preserving Federated Learning in Heterogeneous Data Scenario
Chen, X., Tian, Y., Wang, S., Yang, K., Zhao, W., & Xiong, J. (2025) · Information Sciences · doi:10.1016/j.ins.2024.121849 · Cited by 11
Ullah, I., Deng, X., Pei, X., Mushtaq, H., Uzair, M., & Qayyum, S. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111705 · Cited by 12
Zhou, Y., Wang, R., Liu, J., Wu, D., Yu, S., & Wen, Y. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3325889 · Cited by 8
“There exist a large body of works on privacy-preserving federated learning based on techniques such as homomorphic encryption (HE) and secure multi-party computing (MPC) [20], [21], [22], [23], [24].”
BackgroundZhou, Z., Wang, N., Liu, J., Fu, J., & Deng, L. (2024) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.8257 · Cited by 8
“Miao et al. 2 designed a privacy-preserving Byzantine-robust Federated Learning scheme based on blockchain, which uses blockchain to facilitate transparent processes.”
BRFL: A blockchain-based byzantine-robust federated learning model
Li, Y., Xia, C., Li, C., & Wang, T. (2024) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2024.104995 · Cited by 9
Chen, Y., Linglongyan, & Ai, D. (2024) · IEEE Access · doi:10.1109/access.2024.3493112 · Cited by 10
“The typical statistical indexes include cosine similarity and trimmed median [25], multi-krum [70] and mid-value clustering [69].”
BackgroundInfluentialAn End-Process Blockchain-Based Secure Aggregation Mechanism Using Federated Machine Learning
Mbonu, W. E., Maple, C. R., & Epiphaniou, G. (2023) · Electronics · doi:10.3390/electronics12214543 · Cited by 8
“Miao et al. [27] proposed an FL privacy preserving scheme based on a Blockchain network.”
MethodClustered federated learning based on nonconvex pairwise fusion
Yu, X., Liu, Z., Wang, W., & Sun, Y. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120956 · Cited by 12
Self-citationVoltran: Unlocking Trust and Confidentiality in Decentralized Federated Learning Aggregation
Wang, H. H., Cai, Y., Wang, J., Ma, C., Ge, C., Qu, X., & Zhou, L. Q. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3472531 · Cited by 8
“Scheme [9] proposes a homomorphic encryption-based FL scheme.”
BackgroundMethodEvolutionary Medical Data Modeling and Sharing via Federated Learning Over Sharded Blockchain
Zhang, M., Lin, F., Tian, L., Jia, R., Zheng, Z., & Li, M. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3389593 · Cited by 7
“Local models are stored on blocks and verified by every participant to ensure data authenticity, preventing potential malicious behavior by the central server [11].”
BackgroundZhao, Y., Qu, Y., Xiang, Y., Chen, F., & Gao, L. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3399653 · Cited by 10
“VariousBFLsolutions[5], [6],[7],[8],[9]aredevelopedtofulfilltheemergingdemands indifferentscenarios,whereoneofthemostcommonBFL typologiesisthefully-coupledscheme,asshowninFig.1.”
Low Complexity Byzantine-Resilient Federated Learning
Gouissem, A., Hassanein, S., Abualsaud, K., Yaacoub, E. E., Mabrok, M. A., Abdallah, M. M., Khattab, T. M., & Guizani, M. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3482727 · Cited by 9
“The Secure Cosine is also used in [30] in conjunction with Blockchain and homomorphic encryption to provide secure and transparent aggregation.”
DualGuard: Obfuscated Federated Learning With Two-Party Secure Robust Aggregation
Pan, H., Bao, H., Guan, M., Li, Z., Huang, C., & Dai, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3533087 · Cited by 7
“Miao et al. [26] proposed PBFL, which is based on the idea of Fltrust [24], encrypts the data using the CKKS [39] and completes the computation of the cosine similarity through the collaboration of dual servers.”
InfluentialYin, H., Huang, X., Liang, C., Cao, B., & Zhou, M. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3573798 · Cited by 7
“After receiving the new site, the associated RSU will verify its validity and evaluate the model accuracy using a small dataset D 0 provided by the training task publisher, which could determine the more “promising” direction of the global model update [30].”
Federated learning with enhanced cryptographic security for vehicular cyber-physical systems
Babbar, H., Rani, S., & Shabaz, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-14341-0 · Cited by 7
“Here, we use federated learning to translate raw data from several parties into learnt data models 10,11 , hence learning the data features across multiple parties.”
AIFL: Ensuring Unlinkable Anonymity and Robust Incentive in Cross-Device Federated Learning
Chen, X., Gao, Y., & Deng, H. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3417003 · Cited by 8
“In PBFL Miao et al. [24] utilized cosine similarity to identify dishonest clients and blockchain to facilitate a transparent process.”
BackgroundMethodFlower Full-Compliant Implementation of Federated Learning with Homomorphic Encryption
Catalfamo, A., Carnevale, L., Garofalo, M., & Villari, M. (2024) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc61673.2024.10733641 · Cited by 7
“The research in [10] performs a similar approach.”
MethodEnsuring trustworthy and secure IoT: Fundamentals, threats, solutions, and future hotspots
Huang, M., Peng, Q., Zhu, X., Deng, T., Cao, R., & Liu, W. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111218 · Cited by 8
A Lightweight Homomorphic Encryption Federated Learning Based on Blockchain in IoV
Du, D., Zhao, W., Wei, L., Lu, S., & Wu, X. (2022) · IEEE Smart World Congress (SWC) · doi:10.1109/smartworld-uic-atc-scalcom-digitaltwin-pricomp-metaverse56740.2022.00148 · Cited by 7
“[18] combined homomorphic encryption with federated learning to propose a privacy-preserving federated learning scheme to address the Byzantine attack problem in federal learning.”
BackgroundUllah, I., Deng, X., Pei, X., & Mushtaq, H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8487-5_29 · Cited by 7
EVFL-DCs: Enhancing verifiability of federated learning by double commitments based on blockchain
Wei, Q., Wu, X., Liu, Z., & Rao, G. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111097 · Cited by 6
Self-citationESFL: Accelerating Poisonous Model Detection in Privacy-Preserving Federated Learning
Zeng, H., Lou, J., Li, K., Wu, C., Xue, G., Luo, Y., Cheng, F., Zhao, W., & Li, J. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3541633 · Cited by 6
Personalized Decentralized Federated Learning: A Privacy-Enhanced and Byzantine-Resilient Approach
Zhang, A., Zhao, P., Lu, W., & Zhang, G. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3545905 · Cited by 6
“[43] adopted cosine similarity to exclude the malicious gradients and utilized fully homomorphic encryption to provide privacy protection.”
Zhu, X., & Li, H. (2025) · Applied Sciences · doi:10.3390/app15105472 · Cited by 8
Self-citationGuo, P., Xu, S., & Liang, W. (2025) · Intelligent Computing · doi:10.34133/icomputing.0132 · Cited by 6
Yu, J., Zhang, H., Xia, Q., Zou, Y., & Liu, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3623924 · Cited by 6
“Similarly, the works [27], [28] combined HE and SMC as the underlying foundation to remove encrypted malicious model updates.”
InfluentialZhao, P., Su, N., Wang, Y., Sun, S., & Li, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3633747 · Cited by 6
“PBFL [75] uses fully homomorphic encryption to provide secure aggregation for local model control.”
FedSteg: Coverless Steganography‐Based Privacy‐Preserving Decentralized Federated Learning
Xu, M., & Lin, Y.-G. (2024) · IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING · doi:10.1002/tee.24085 · Cited by 6
“Alternatively, compression algorithms can be implemented to decrease the message size, Different from the existing researches [16–19], the generation of private and public keys in the above cryptosystem and the encryption and decryption of data does not require a fully trusted KGC.”
BackgroundMethodInfluentialZero Trust Consumer IoT With Robust Federated Learning Over Main-Side Blockchain
Zhu, H. J., Xue, X., Xu, M., & Kim, B. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3471921 · Cited by 6
“We compared FL-msCIoT framework with six state-of-the-art baseline meth-ods: FedAvg [30], FedSteg [31], RFA [32], PBFL [33], VOSA [34], and SVeriFL [35].”
Sun, H., Zhang, Y., Zhuang, H., Li, J., Xu, Z., & Wu, L. (2024) · The Computer Journal · doi:10.1093/comjnl/bxae086 · Cited by 7
Can We Trust the Similarity Measurement in Federated Learning?
Wang, Z., Hu, Q., Zou, X., Hu, P., & Cheng, X. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3516567 · Cited by 6
“Researchers design defenses based on various metrics to evaluate local models before aggregation, assuming that the poisoned local model is sig-nificantly di ff erent from the benign one [12], [13], [14].”
FLock: Robust and Privacy-Preserving Federated Learning based on Practical Blockchain State Channels
Chen, R., Dong, Y., Liu, Y., Fan, T., Li, D., Guan, Z., Liu, J., & Zhou, J. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714666 · Cited by 6
Federated and Online Dynamic Spectrum Access for Mobile Secondary Users
Dong, X., You, Z., Liu, X., Guo, Y., Shen, Y., & Gong, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3280933 · Cited by 6
“Due to the inherent advantages of protecting user privacy, an increasing number of researchers have applied FL to solve many problems in different fields (e.g., [18], [19], [20]).”
BackgroundZhu, B., Ling, N., & Zhang, Y. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.03.034 · Cited by 5
RetractedWei, Z., Wang, J., Zhao, Z., & Zhao, Z. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103345 · Cited by 8
Wu, J., Luo, F., Sun, T., Wang, H., & Zhang, W. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3617070 · Cited by 7
“Then, each user downloads the global gradient g ( t ) for local update. i ]] } i ∈ [1 ,n ] and perform aggregating of the local gradients.”
Xiong, H., Lv, J., Man, D., Zhu, Y., Liu, T., Wang, H., Xu, C., & Yang, W. (2025) · Computer Communications · doi:10.1016/j.comcom.2025.108272 · Cited by 5
Zeng, W., Xu, X., Zhang, Q., Shi, J., Guan, Z., Li, S., & Qin, Z. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3664479 · Cited by 7
A Secure and Lightweight Aggregation Method for Blockchain-based Distributed Federated Learning
Huang, H., Duan, L., Li, C., & Ni, W. (2024) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws62655.2024.00066 · Cited by 5
“Miao et al. [28] designed a privacy-preserving Byzantine-robust FL scheme based on blockchain systems.”
MethodRobust and privacy-preserving federated learning scheme based on ciphertext-selected users
Wang, X., Liu, Z., & Huang, B. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111072 · Cited by 5
Self-citationAntidoteFL: Enhancing defense against poisoning attacks in federated learning
Liu, Y., Zhang, H., Wang, M., Xie, Q., & Sun, Z. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111427 · Cited by 5
Resisting Poisoning Attacks in Federated Learning via Dual-Domain Distance and Trust Assessment
Wang, Z., Zhang, Z., Li, Z., Wu, Y. X., Liu, Y., Li, M., Li, X., Liu, Y., An, J., Liang, W., et al. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3589061 · Cited by 5
“This approach has been widely adopted in sectors like medicine, finance, and social media to collaboratively train models while safeguarding data privacy [2].”
Pu, L., Gu, J., Lin, C., & Huang, X. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3597223 · Cited by 6
“Miao et al. [13] utilized fully HE to enable secure aggregation, while incorporating a blockchain system to enhance transparency and regulatory compliance.”
A Privacy Robust Aggregation Method Based on Federated Learning in the IoT
Li, Q., Wang, X., & Ren, S. (2023) · Electronics · doi:10.3390/electronics12132951 · Cited by 6
Decentralized Defense: Leveraging Blockchain against Poisoning Attacks in Federated Learning Systems
Thennakoon, R., Wanigasundara, A., Weerasinghe, S., Seneviratne, C., Siriwardhana, Y., & Liyanage, M. (2024) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc51664.2024.10454688 · Cited by 5
“The off-chain computation replaces on-chain aggregation which consumes higher gas costs and computational power[7].”
BackgroundSun, K., Liu, L., Pan, Q., Li, J., & Wu, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3409610 · Cited by 6
“[6], [7], [8].”
Gao, H., Pan, X., Zhang, X., Ye, K., Zhang, P., & Sun, L. (2023) · International Conference on Computer Science and Communication Technology (ICCSCT) · doi:10.1117/12.3009373 · Cited by 5
“Miao et al.(30) proposed PBFL, a blockchain-based confidential Byzantine robust federated learning scheme.”
BackgroundZuo, C., Xu, P., Song, Y., Lu, J., Yuan, C., & Li, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-16830-8 · Cited by 4
“Devices with poor behavior, whether due to adversarial attacks or unstable conditions, can negatively affect model training and must be identified and mitigated 17,18 .”
Saidi, A. A., Amira, A., & Nouali, O. (2025) · Cluster Computing · doi:10.1007/s10586-025-05715-0 · Cited by 4
“Miao et al. [40] combined CKKS encryption with FLTrust-based anomaly detection on block-chain to resist poisoning.”
Algethami, W., Wu, G., Alshami, F., & Ali, M. A. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123389 · Cited by 4
Robust and Secure Aggregation Scheme for Federated Learning
Tang, W., Li, J., Dong, C., Miao, Y., Li, Q., Li, N., Deng, S., & Ji, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3509222 · Cited by 4
“Miao et al. [34] applied fully homomorphic encryption (FHE) to designate the solver to compute cosine similarity with ciphertext, which was decrypted by another server for aggregation.”
Self-citationLightweight Secure Aggregation for Personalized Federated Learning with Backdoor Resistance
Fan, T., Chen, X., Dong, Y., Chen, X., Xuan, Y., & Jing, W. (2024) · Annual Computer Security Applications Conference · doi:10.1109/acsac63791.2024.00071 · Cited by 4
“In addition, PBFL [38] and FLEDGE [11] combine blockchain with robust defense strategies, with the former using similarity detection techniques and the latter incorporating clustering techniques to filter poisoned updates.”
Robust Federated Learning Algorithm Based on Chaotic Encryption and Dual-Server Detection
Kang, S., Wu, Y., Wang, Y., Wang, Q., & Liang, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3565598 · Cited by 4
“Miao et al. [30] proposed the PBF L algorithm.”
zkFL: Verifiable Byzantine-Robust Federated Learning Against Malicious Servers
Tang, X., Li, M., Zhang, T., Lin, Y., Zhu, L., Zhou, C., & Liu, X. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3622060 · Cited by 4
“FL is a distributed machine learning paradigm that enables multiple clients to collaboratively train a global model without sharing their private data [10], [87], [88], [89], [90].”
Du, M., Zhang, M., Liu, L., Xu, K., & Yin, Q. (2023) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3605573.3605592 · Cited by 4
“Utilizing the transparency and tamper-proof of blockchain, smart contracts can effectively filter Byzantine workers in federated learning even within a decentralized setting[24][17].”
BackgroundAn Efficient Federated Learning Framework for Privacy-Preserving Data Aggregation in IoT
Shi, R., Wei, L., & Zhang, L. (2023) · Conference on Privacy, Security and Trust · doi:10.1109/pst58708.2023.10320198 · Cited by 4
“We compare our work with PSA and the CKKS-based scheme [27] and the Paillier-based scheme [28].”
ResultWan, T., Jiang, T., Liao, W., & Jiang, N. (2024) · International Journal of Intelligent Systems · doi:10.1155/2024/6402026 · Cited by 4
“In the context of FL, a privacy-preserving Byzantine-robust federated learning (PBFL) scheme based on blockchain was proposed in [18], which achieves convergence and provides privacy protection on diferent datasets.”
MethodB2DFL: Bringing butterfly to decentralized federated learning assisted with blockchain
Wang, H. H., Cai, Y., Tao, Y., Wang, L., Li, Y., & Zhou, L. (2024) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2024.104978 · Cited by 4
Blockchain-Based Edge Computing Service With Dynamic Entry and Exit Mechanism
He, Q., Feng, Z., Fang, H., Wang, X., Zhao, L., Yu, K., & Choo, K. R. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3570646 · Cited by 4
“Blockchainisapromisingtechnologythatleveragesapeer-to-peernetworktopologywithimmutable,transparent,and tamper-resistant data ledger [10], [11], [12].”
Self-citationA Small-Size FHE Scheme for Better Privacy Protection of IoT
Song, W., Zhang, W., Tang, D., & Hu, B. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3336158 · Cited by 3
Mitigating Poisoning Attacks in Federated Learning Through Deep One-Class Classification
Zhang, A., Zhao, P., Lu, W., Zhou, Y., Zhang, W., & Zhang, G. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3564476 · Cited by 3
“[1], [3], [6], [8], [9], [12], [17], [18] are only applicable to a small malicious users scale (i.e., Byzantine ratio) and the independent and identically distributed (i.e., IID) local datasets.”
InfluentialAhmad, M., Habib, S., & Tariq, F. (2025) · VFAST Transactions on Software Engineering · doi:10.21015/vtse.v13i2.2163 · Cited by 6
Robust aggregation algorithms for federated learning in unreliable network environments
Zeng, Z., Yang, S., & Ding, G. (2025) · Journal of Computing and Electronic Information Management · doi:10.54097/n0dpaf43 · Cited by 3
Li, K., Liang, Y., Lió, P., Ni, W., Dressler, F., Crowcroft, J., & Akan, Ö. B. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3636440 · Cited by 3
“At user n , the cosine similarity among the received model updates from its ˜ n neighbors can be measured, which is used as a defense mechanism [27], [28] to detect potential UIP model updates.”
Zhang, Y., Liu, Z., Xu, Y., Deng, N., Luo, X., & Lin, F. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3617901 · Cited by 3
Self-citationEfficient Mobile-Cloud Collaborative Aggregation for Federated Learning With Latency Resilience
Tang, W., Li, J., Zhang, X., Miao, Y., Su, Z., & Deng, R. H. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3642433 · Cited by 3
“Moreover, Miao et al. [19] integrated CKKS and blockchain technologies to achieve a trustworthy training process.”
Self-citationLi, L., Guo, C., Tang, X., Choo, K.-K. R., & Liu, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3648540 · Cited by 3
“Similarly, [14] and [15] combine blockchain with HE to protect model updates in DFL, but the blockchain component introduces additional computational overhead, such as on-chain operations.”
Self-citationZhang, H., He, X., Wu, J., & Wang, Q. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3650413 · Cited by 3
“To mitigate Byzantine attacks, Byzantine-robust aggregation methods [10], [17], [18], [19], [20], [21], [22], [23], [24], [25], [26], [27] are proposed to conduct robust and accurate global model training despite the presence of a certain number of malicious clients.”
Two-Dimensional Privacy-Preserving Federated Learning Scheme Against Poisoning Attacks
Gu, K., Zhao, W., Tan, J., Yang, Z., Li, X., & Weijia Jia, B. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3656703 · Cited by 3
“Miao et al. [18] leveraged Fully Homomor-phic Encryption (FHE) to securely compute cosine similarity on ciphertexts for identifying malicious gradients.”
TDLearning: Trusted Distributed Collaborative Learning Based on Blockchain Smart Contracts
Liu, J., Hai, X., & Li, K. (2023) · Future Internet · doi:10.3390/fi16010006 · Cited by 4
“Miao et al. [21] implemented homomorphic encryption-based federated learning, where the encrypted intermediate parameters are stored in a blockchain in order to prevent the malicious tampering of the parameters.”
BackgroundPutra, M. A. P., Karna, N. B. A., Zainudin, A., Kim, D., & Lee, J. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101287 · Cited by 3
A Federated Learning Framework Based on Blockchain and Adaptive Differential Privacy
Liu, Y., Li, Q., & Xin, Z. (2024) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec60942.2024.10733270 · Cited by 3
“Building upon this foundation, Miao et al.[4] developed a cosine similarity method to detect malicious gradient updates uploaded by hostile participants.”
MethodFederated learning with bilateral defense via blockchain
Xiao, J., Nie, H., Yi, Z., Tang, X., & Lu, S. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107199 · Cited by 4
Fed-HA: A Privacy-Preserving Robust Federated Learning Scheme based on Homomorphic Assessment
Xu, W., Xu, X., & Wang, H. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104144 · Cited by 4
Ali, A. S., Zaaba, Z. F., Singh, M. M., Anuar, N. B., & Shariff, M. R. B. M. (2025) · International Journal of Information Security · doi:10.1007/s10207-025-01111-2 · Cited by 8
“Researchers have proposed different techniques for protecting information, including federated learning to protect model integrity [120] and spatial range queries on encrypted data within cloud servers [121].”
PPFL-IDS: Privacy-Preserving Federated Learning Based IDS Against Poisoning Attacks
Xu, M., & Li, X. (2023) · Mobile Networks and Applications · doi:10.1007/s11036-023-02231-6 · Cited by 3
“AlthoughsomePPFL studies canresist poisoning attacks [28–30], there is no research on the corresponding poisoning attack and anti-attack strategy for intrusion detection systems.”
SKYMASK: Attack-Agnostic Robust Federated Learning with Fine-Grained Learnable Masks
Yan, P., Wang, H., Song, T., Hua, Y., Ma, R., Hu, N., Haghighat, M. R., & Guan, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72655-2_17 · Cited by 3
FedCrypt: A Dynamic White-Box Watermarking Scheme for Homomorphic Federated LearningPreprint
Lansari, M., Bellafqira, R., Kapusta, K., Kallas, K., Thouvenot, V., Bettan, O., & Coatrieux, G. (2024) · doi:10.36227/techrxiv.172114666.63343276/v1 · Cited by 3
Decentralized Federated Learning towards Communication Efficiency, Robustness, and Personalization
Zhang, A., Zhao, P., Lu, W., & Zhang, G. (2025) · ACM Transactions on Sensor Networks · doi:10.1145/3730587 · Cited by 2
“In order to evaluate the Byzantine robustness of D-CERP under two cases of adversary knowledge mentioned in Section 3, we launch the following three attacks, which are also explored in previous literatures [9, 22, 26–28].”
InfluentialA Byzantine-robust federated learning against adversarial–majority attacks
Shi, Y., Hu, X., Bai, S., Liu, Y., & Lin, H. W. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07619-7 · Cited by 2
“However, FLTrust relies on a clean validation dataset whose [15], which employs a filtering mechanism similar to FLTrust [13], relying on a clean validation dataset maintained on the server.”
SmartFL: Simple majority rule based Byzantine-robust federated learning
Dong, Q., Gao, Y., Zhou, C., Yang, S., Kuang, B., & Fu, A. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103555 · Cited by 2
Breaking the Mainchain Barrier of Blockchain Sharding Architecture for Federated Learning
Qi, J., Ding, D., Yue, P., Zhang, H., Tian, L., Chen, Y.-C., Lou, J., Yu, J., Xiao, Q., Li, J., et al. (2025) · International Workshop on Quality of Service · doi:10.1109/iwqos65803.2025.11143398 · Cited by 2
“Miao et al. [14] mitigated the impact of central servers and malicious clients by proposing a privacy-preserving, Byzantine-robust federated learning scheme based on blockchain.”
Bhardwaj, T., & Sumangali, K. (2025) · Scientific Reports · doi:10.1038/s41598-025-21852-3 · Cited by 2
“Miao et al. 20 introduced a blockchain-based Privacy-preserving Byzantine-robust Federated Learning (PBFL) system reduces central server influence and protects against malicious clients.”
Xue, K., Li, J., Xue, R., Xue, Y., & Zhao, J. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3632902 · Cited by 3
“PBFL [72] utilizes CKKS to protect privacy and cosine similarity to detect malicious models.”
PPFPL: Cross-Silo Privacy-Preserving Federated Prototype Learning Against Data Poisoning Attacks
Zhang, H., Yu, J., Xu, F., Hu, C., Zhang, Y., Wang, X., Yu, Z., & Zhang, X. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3643391 · Cited by 2
“Other comparable schemes [16] [19] [15] adopt homomorphic encryption on gradients, resulting in an encryption overhead O ( gT ch ) , where g denotes the number of gradient parameters.”
InfluentialFRIDA: Free-rider detection using privacy attacks
Recasens, P. G., Horváth, Á., Gutierrez-Torre, A., Torres, J., Berral, J. L., & Pejó, B. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104357 · 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 2
“To accommodate real-world scenarios, multiple servers can be used for Secure Multi-party Computation (SMC) [39] in VPFL, and decentralized structures like blockchain can be introduced to solve single point of failure problem [14].”
MethodCollaborative Construction Method of Biomedical Knowledge Graph Based on Multi-Blockchain
Wang, J., Xie, Z., Xin, H., Li, P., Zhang, Y., Xiong, X., & Lin, J. C. (2024) · Distributed Ledger Technologies Research and Practice · doi:10.1145/3674153 · Cited by 2
“Considering that the system’s ability to correctly process collaborative user data is also an important indicator for verifying system performance, the Jaccard Similarity [33] and Cosine Similarity [21] are used as evaluation indicators.”
An Enclave-Aided Byzantine-Robust Federated Aggregation Framework
Yao, J., Song, C., Li, H., Wang, Y., Yang, Q., & Wang, L. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10570631 · Cited by 2
Self-citationOptimizing Federated Learning through Lightweight and Scalable Blockchain
Andronikidis, G., Niotis, G., Eleftheriadis, C., Kyranou, K., Nikoletseas, S., & Sarigiannidis, P. G. (2024) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss-iot61029.2024.00075 · Cited by 2
“Solutions for Byzantine attacks in Blockchain FL, proposed in [30], leverage blockchain and homomorphic encryption, while [24] focuses on effective client selection.”
BackgroundDou, K., He, F., Shang, F., Li, X., Dong, Y., & Liu, J. (2024) · IEEE International Conference on Big Data and Artificial Intelligence (BDAI) · doi:10.1109/bdai62182.2024.10692438 · Cited by 2
“Literature [18] utilizes fully homomorphic encryption and blockchain technology to address privacy concerns and trustworthiness issues in federated learning.”
BackgroundTowards Practical Homomorphic Aggregation in Byzantine-Resilient Distributed Learning
Choffrut, A., Guerraoui, R., Pinot, R., Sirdey, R., Stephan, J., & Zuber, M. (2024) · International Middleware Conference · doi:10.1145/3652892.3700783 · Cited by 7
“Finally, a handful of prior works [45, 47, 57, 69] investigate the use of HE to grant privacy to Byzantine robust ML algorithms.”
Chen, S., Zhou, T., Xie, H., & Yang, X. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104039 · Cited by 2
Zhang, H., Yu, Z., Wang, G., Xu, F., Zhang, Y., Hu, C., Wang, X., & Yu, J. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3620529 · Cited by 2
“Topreventpoisoningattackswithoutcompromising privacy,existingsolutions[20],[21],[22],[23]adopt HomomorphicEncryption(HE)toanalyzetheencrypted modelupdates.”
InfluentialDefending Against Poisoning Attacks in Federated Prototype Learning on Non-IID Data
Zhang, J., Zhang, H., Wang, G., & Dong, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71467-2_6 · Cited by 1
A Survey on Securing Image-Centric Edge Intelligence
Li, T., Hu, H., Gabbouj, M., Ye, Q., Xiang, Y., Li, J., & Li, L. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3700792 · Cited by 1
EMAFL: Evolutionary Momentum Auxiliary Adaptive Accelerating Federated Learning
Qiao, D., Guo, S., Chen, X., Zhou, P., Zhang, D., & Zhang, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3523970 · Cited by 1
“Fortunately, federated learning (FL) [6], [7], [8], as an outstanding artificial intelligence technique, has introduced a novel application paradigm in the field of EC.”
TTFL: Towards Trustworthy Federated Learning with Arm Confidential Computing
Sun, L., Zhu, J., Chang, B., Xu, Y., Yang, B., Wu, H., Xu, F., & Zhong, S. (2024) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom63139.2024.00132 · Cited by 1
“Previous works [35]–[37] obtain the root dataset by sampling data from FL clients, which is not practical.”
InfluentialXie, Q., & Zhao, Y. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111493 · Cited by 2
A Robust Decentralized Federated Aggregation for Heterogeneous Data via Blockchain System
Zheng, M., & Wang, L.-E. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3586789 · Cited by 1
“In the context of Byzantine node detection in FL with non-IID data, a Byzantine robust variance reduction stochastic gradient descent (SGD) method is proposed by Miao et al. [24].”
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
