journal article·2026-02-11Open access

BE-DPFL: A Blockchain-Enhanced Privacy-Preserving Federated Learning Framework for Secure Edge Network Collaboration

Wangjing Jia, Tao Xie

Applied Sciences· Volume 16· Issue 4

Abstract

Against the deep integration of digital transformation and AI, cross-institutional collaborative modeling hinges on efficient data circulation, yet data silos and privacy regulations hinder traditional centralized training. Federated Learning (FL) keeps data local but faces issues like weak centralized trust, inadequate privacy protection, and poor robustness in edge networks. Existing improvements, including via differential privacy (DP) and blockchain, among others, still suffer from centralized budget allocation, low consensus efficiency, or single-point-of-failure addressing, failing to jointly optimize trust, performance, and privacy. The limitations are exacerbated in high-frequency, resource-constrained edge environments. To tackle these challenges, this paper proposes BE-DPFL, a blockchain-enhanced differentially private FL framework that integrates on-chain trusted supervision and off-chain efficient training. It builds a lightweight blockchain trust layer with FL-PBFT consensus and smart contracts, introduces Random Projection–ADMM optimization, and designs a multi-objective adaptive gradient clipping/noise injection strategy. Experiments on CIFAR-10 and ChestX-ray14 demonstrate that BE-DPFL outperforms mainstream methods in consensus efficiency, communication overhead, privacy-accuracy balance, and robustness. It reduces communication costs by over 97%, achieves 100% privacy compliance, and maintains stable performance even under high disturbances. Ablation studies confirm the significant contributions of core components.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Privacy-Preserving Technologies in Data · Blockchain Technology Applications and Security · IoT and Edge/Fog Computing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China

Shanxi Police College, Taiyuan 030401, China

References (39)

Show source-provided references
1. A survey on federated learning10.1016/j.knosys.2021.106775 ↗
2. Machine learning approaches in medical image analysis: From detection to diagnosis10.1016/j.media.2016.06.032 ↗
3. ESG rating and financial risk of mining industry companies10.1016/j.resourpol.2023.104308 ↗
4. Industrial Internet of Things and its applications in industry 4.0: State of the art10.1016/j.comcom.2020.11.016 ↗
5. Anomaly detection and defense techniques in federated learning: A comprehensive review10.1007/s10462-024-10796-1 ↗
6. Differential privacy for deep and federated learning: A survey10.1109/ACCESS.2022.3151670 ↗
7. Low-latency federated learning over wireless channels with differential privacy10.1109/JSAC.2021.3126052 ↗
8. A survey on blockchain technology and its security10.1016/j.bcra.2022.100067 ↗
9. Blockchain-empowered federated learning: Challenges, solutions, and future directions10.1145/3570953 ↗
10. Securing federated learning with blockchain: A systematic literature review10.1007/s10462-022-10271-9 ↗
11. Federated learning with differential privacy: Algorithms and performance analysis10.1109/TIFS.2020.2988575 ↗
12. Truex, S., Liu, L., Chow, K.H., Gursoy, M.E., and Wei, W. (2020, January 27). LDP-Fed: Federated learning with local differential privacy. Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and Networking, Crete, Greece.10.1145/3378679.3394533 ↗
13. Personalized federated learning with differential privacy10.1109/JIOT.2020.2991416 ↗
14. An adaptive federated learning scheme with differential privacy preserving10.1016/j.future.2021.09.015 ↗
15. Dynamic personalized federated learning with adaptive differential privacy
16. Efficient federated learning privacy preservation method with heterogeneous differential privacy10.1016/j.cose.2024.103715 ↗
17. Federated learning data protection scheme based on personalized differential privacy in psychological evaluation10.1016/j.neucom.2024.128653 ↗
18. Differential privacy for multi-modal federated learning with modality selection10.1109/TIFS.2025.3598587 ↗
19. Does differential privacy really protect federated learning from gradient leakage attacks?10.1109/TMC.2024.3417930 ↗
20. Communication-efficient and privacy-preserving federated learning via joint knowledge distillation and differential privacy in bandwidth-constrained networks10.1109/TVT.2024.3423718 ↗
21. Blockchain and federated learning for privacy-preserved data sharing in industrial IoT10.1109/TII.2019.2942190 ↗
22. Blockchain-enabled federated learning data protection aggregation scheme with differential privacy and homomorphic encryption in IIoT10.1109/TII.2021.3085960 ↗
23. DS2PM: A data-sharing privacy protection model based on blockchain and federated learning10.1109/JIOT.2021.3134755 ↗
24. ShareChain: Blockchain-enabled model for sharing patient data using federated learning and differential privacy10.1111/exsy.13131 ↗
25. Differential privacy and blockchain-empowered decentralized graph federated learning-enabled UAVs for disaster response10.1109/JIOT.2023.3332216 ↗
26. Ensuring zero trust IoT data privacy: Differential privacy in blockchain using federated learning10.1109/TCE.2024.3444824 ↗
27. Blockchain based secure federated learning with local differential privacy and incentivization10.1109/TP.2024.3487819 ↗
28. A Lightweight Authentication Scheme Based on Consortium Blockchain for Cross-Domain IoT
29. A survey on differential privacy for unstructured data content
30. A two-level ADMM algorithm for AC OPF with global convergence guarantees10.1109/TPWRS.2021.3073116 ↗
31. ULS-PBFT: An ultra-low storage overhead PBFT consensus for blockchain10.1016/j.bcra.2023.100155 ↗
32. Beyond data poisoning in federated learning10.1016/j.eswa.2023.121192 ↗
33. On the convergence of alternating direction lagrangian methods for nonconvex structured optimization problems
34. Xiao, H., Xiang, Z., Wang, D., and Devadas, S. (2023). A theory to instruct differentially-private learning via clipping bias reduction. 2023 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA, 22–24 May 2023, IEEE.10.1109/SP46215.2023.10179409 ↗
35. The stochastic multi-gradient algorithm for multi-objective optimization and its application to supervised machine learning10.1007/s10479-021-04033-z ↗
36. Thakkar, P., Nathan, S., and Viswanathan, B. (2018, January 25–28). Performance benchmarking and optimizing hyperledger fabric blockchain platform. Proceedings of the 2018 IEEE 26th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), Milwaukee, WI, USA.10.1109/MASCOTS.2018.00034 ↗
37. Advancing chest X-ray diagnostics: A novel CycleGAN-based preprocessing approach for enhanced lung disease classification in ChestX-Ray1410.1016/j.cmpb.2024.108518 ↗
38. Convolutional deep belief networks on cifar-10
39. A smart healthcare system based on classifier DenseNet 121 model to detect multiple diseases