Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses

Documenti analoghi

• Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
  di: Pawlak, Stanisław, et al.
  Pubblicazione: (2025)
• Heterogeneous Graph Backdoor Attack
  di: Chen, Jiawei, et al.
  Pubblicazione: (2025)
• Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
  di: Obioma, Chibueze Peace, et al.
  Pubblicazione: (2025)
• Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
  di: Shin, Jeongjin, et al.
  Pubblicazione: (2024)
• Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
  di: Min, Rui, et al.
  Pubblicazione: (2024)