EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improved Distributed Backdoor Attacks in Federated Learning by Density-Adaptive Data Poisoning and Projection-Based Gradient Updating

Jian Wang, Hong Shen, Wei Ke, Xue Hua Liu

IEEE Access · 2025 · 13 · 130651-130671

DOI: 10.1109/access.2025.3586416 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Jian Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Development Fund, Macao SAR, Department of Environment and Science of Queensland State Government under Quantum Challenges 2032 Program, Scientific Research Platforms and Projects of Universities in Guangdong Province in 2024.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • Science and Technology Development Fund, Macao SAR
  • Department of Environment and Science of Queensland State Government under Quantum Challenges 2032 Program
  • Scientific Research Platforms and Projects of Universities in Guangdong Province in 2024
  • 2024 Guangdong Province Science and Technology Innovation Strategy Special Fund

Zitieren

APA

Wang, J., Shen, H., Ke, W., & Liu, X. H. (2025). Improved Distributed Backdoor Attacks in Federated Learning by Density-Adaptive Data Poisoning and Projection-Based Gradient Updating. IEEE Access, 13, 130651-130671. https://doi.org/10.1109/access.2025.3586416

Vancouver

Wang J, Shen H, Ke W, Liu XH. Improved Distributed Backdoor Attacks in Federated Learning by Density-Adaptive Data Poisoning and Projection-Based Gradient Updating. IEEE Access. 2025;13:130651-130671. doi:10.1109/access.2025.3586416

BibTeX
@article{Wang2025,
  author = {Wang, Jian and Shen, Hong and Ke, Wei and Liu, Xue Hua},
  title = {Improved Distributed Backdoor Attacks in Federated Learning by Density-Adaptive Data Poisoning and Projection-Based Gradient Updating},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {130651--130671},
  doi = {10.1109/access.2025.3586416}
}
Kostenlos starten →