EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EVFL: Towards Efficient Verifiable Federated Learning via Parameter Reuse and Adaptive Sparsification

Jianping Wu, Chunming Wu, Chaochao Chen, Jiahe Jin, Chuan Zhou

Mathematics · 10.08.2024 · 12 (16) · 2479

DOI: 10.3390/math12162479 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 10.08.2024. Verfasst von Jianping Wu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Major Project of China, 2024 Key R&D Program of Zhejiang Province, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) demonstrates significant potential in Industrial Internet of Things (IIoT) settings, as it allows multiple institutions to jointly construct a shared learning model by exchanging model parameters or gradient updates without the need to transmit raw data. However, FL faces risks related to data poisoning and model poisoning. To address these issues, we propose an efficient verifiable federated learning (EVFL) method, which integrates adaptive gradient sparsification (AdaGS), Boneh–Lynn–Shacham (BLS) signatures, and fully homomorphic encryption (FHE). The combination of BLS signatures and the AdaGS algorithm is used to build a secure aggregation protocol. These protocols verify the integrity of parameters uploaded by industrial agents and the consistency of the server’s aggregation results. Simulation experiments demonstrate that the AdaGS algorithm significantly reduces verification overhead through parameter sparsification and reuse. Our proposed algorithm achieves better verification efficiency compared to existing solutions.

Förderung

  • National Science and Technology Major Project of China
  • 2024 Key R&D Program of Zhejiang Province, China

Zitieren

APA

Wu, J., Wu, C., Chen, C., Jin, J., & Zhou, C. (2024). EVFL: Towards Efficient Verifiable Federated Learning via Parameter Reuse and Adaptive Sparsification. Mathematics, 12(16), 2479. https://doi.org/10.3390/math12162479

Vancouver

Wu J, Wu C, Chen C, Jin J, Zhou C. EVFL: Towards Efficient Verifiable Federated Learning via Parameter Reuse and Adaptive Sparsification. Mathematics. 2024;12(16):2479. doi:10.3390/math12162479

BibTeX
@article{Wu2024,
  author = {Wu, Jianping and Wu, Chunming and Chen, Chaochao and Jin, Jiahe and Zhou, Chuan},
  title = {EVFL: Towards Efficient Verifiable Federated Learning via Parameter Reuse and Adaptive Sparsification},
  journal = {Mathematics},
  year = {2024},
  volume = {12},
  number = {16},
  pages = {2479},
  doi = {10.3390/math12162479}
}
Kostenlos starten →