EUVIMEDEUVIMED entdecken
Crossref

Data Compliance Utilization Method Based on Adaptive Differential Privacy and Federated Learning

Haiyan Kang iD, Bing Wu iD, Chong Zhang iD

International Journal of Neural Systems · 2026

DOI: 10.1142/s0129065725500601 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, 2026. Verfasst von Haiyan Kang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Security, Beijing Information Science and Technology University, Beijing 100192, P. R. China. Hauptthemen laut MEDLINE: Privacy, Computer Security, Machine Learning, Blockchain. Die Arbeit nennt 37 Literaturangaben. Gefördert von: the National Social Science Foundation, China, Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL), as a method that coordinates multiple clients to train models together without handing over local data, is naturally privacy-preserving for data. However, there is still a risk that malicious attackers can steal intermediate parameters and infer the user’s original data during the model training, thereby leaking sensitive data privacy. To address the above problems, we propose an adaptive differential privacy blockchain federated learning (ADP-BCFL) method to accomplish the compliant use of distributed data while ensuring security. First, utilize blockchain to accomplish secure storage and valid querying of user summary data. Second, propose an adaptive DP mechanism to be applied in the process of federal learning, which adaptively adjusts the threshold size of parameter tailoring according to the parameter characteristics, controls the amount of introduced noise, and ensures a good global model accuracy while effectively solving the problem of inference attack. Finally, the ADP-BCFL method was validated on the MNIST, Fashion MNIST datasets and spatiotemporal dataset to effectively balance model performance and privacy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PrivacyComputer SecurityMachine LearningBlockchainHumansFederated Learning

Stichwörter der Autor:innen

Federated learningadaptive differential privacyblockchaindata processing

Autor:innen und Institutionen

  • Department of Information Security, Beijing Information Science and Technology University, Beijing 100192, P. R. China.

ORCID-Profile: Haiyan Kang, Bing Wu, Chong Zhang

Förderung

  • the National Social Science Foundation, China
  • Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing

Zitieren

APA

Kang, H., Wu, B., & Zhang, C. (2026). Data Compliance Utilization Method Based on Adaptive Differential Privacy and Federated Learning. International Journal of Neural Systems. https://doi.org/10.1142/s0129065725500601

Vancouver

Kang H, Wu B, Zhang C. Data Compliance Utilization Method Based on Adaptive Differential Privacy and Federated Learning. International Journal of Neural Systems. 2026. doi:10.1142/s0129065725500601

BibTeX
@article{Kang2026,
  author = {Kang, Haiyan and Wu, Bing and Zhang, Chong},
  title = {Data Compliance Utilization Method Based on Adaptive Differential Privacy and Federated Learning},
  journal = {International Journal of Neural Systems},
  year = {2026},
  doi = {10.1142/s0129065725500601}
}
Kostenlos starten →