EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Survey on Backdoor Attacks on Deep Learning: Current Trends, Categorization, Applications, Research Challenges, and Future Prospects

Muhammad Abdullah Hanif, Nandish Chattopadhyay, Bassem Ouni, Muhammad Shafique

IEEE Access · 2025 · 13 · 93190-93221

DOI: 10.1109/access.2025.3571995 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Muhammad Abdullah Hanif und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 162 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Technology Innovation Institute (TII) under the "CASTLE: Cross-Layer Security for Machine Learning Systems IoT" project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • Technology Innovation Institute (TII) under the "CASTLE: Cross-Layer Security for Machine Learning Systems IoT" project

Zitieren

APA

Hanif, M. A., Chattopadhyay, N., Ouni, B., & Shafique, M. (2025). Survey on Backdoor Attacks on Deep Learning: Current Trends, Categorization, Applications, Research Challenges, and Future Prospects. IEEE Access, 13, 93190-93221. https://doi.org/10.1109/access.2025.3571995

Vancouver

Hanif MA, Chattopadhyay N, Ouni B, Shafique M. Survey on Backdoor Attacks on Deep Learning: Current Trends, Categorization, Applications, Research Challenges, and Future Prospects. IEEE Access. 2025;13:93190-93221. doi:10.1109/access.2025.3571995

BibTeX
@article{Hanif2025,
  author = {Hanif, Muhammad Abdullah and Chattopadhyay, Nandish and Ouni, Bassem and Shafique, Muhammad},
  title = {Survey on Backdoor Attacks on Deep Learning: Current Trends, Categorization, Applications, Research Challenges, and Future Prospects},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {93190--93221},
  doi = {10.1109/access.2025.3571995}
}
Kostenlos starten →