Defending against Backdoor Attacks in Federated Learning by Using Differential Privacy and OOD Data Attributes
Computer Modeling in Engineering & Sciences · 2025 · 143 (2) · 2417-2428
DOI: 10.32604/cmes.2025.063811 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Modeling in Engineering & Sciences, 2025. Verfasst von Qingyu Tan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Tan, Q., Li, Y., & Shin, B. (2025). Defending against Backdoor Attacks in Federated Learning by Using Differential Privacy and OOD Data Attributes. Computer Modeling in Engineering & Sciences, 143(2), 2417-2428. https://doi.org/10.32604/cmes.2025.063811
Vancouver
Tan Q, Li Y, Shin B. Defending against Backdoor Attacks in Federated Learning by Using Differential Privacy and OOD Data Attributes. Computer Modeling in Engineering & Sciences. 2025;143(2):2417-2428. doi:10.32604/cmes.2025.063811
BibTeX
@article{Tan2025,
author = {Tan, Qingyu and Li, Yan and Shin, Byeong-Seok},
title = {Defending against Backdoor Attacks in Federated Learning by Using Differential Privacy and OOD Data Attributes},
journal = {Computer Modeling in Engineering & Sciences},
year = {2025},
volume = {143},
number = {2},
pages = {2417--2428},
doi = {10.32604/cmes.2025.063811}
}
EUVIMED