DOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated Constraints

Documenti analoghi

• Stealthy Backdoor Attack via Confidence-driven Sampling
  di: He, Pengfei, et al.
  Pubblicazione: (2023)
• Stealthy Targeted Backdoor Attacks against Image Captioning
  di: Fan, Wenshu, et al.
  Pubblicazione: (2024)
• Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning
  di: Lyu, Xiaoting, et al.
  Pubblicazione: (2024)
• SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
  di: Choe, Minyeong, et al.
  Pubblicazione: (2024)
• Dullahan: Stealthy Backdoor Attack against Without-Label-Sharing Split Learning
  di: Pu, Yuwen, et al.
  Pubblicazione: (2024)