Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks

Documenti analoghi

• Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
  di: Zhao, Shuai, et al.
  Pubblicazione: (2024)
• Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
  di: Lyu, Xingyu, et al.
  Pubblicazione: (2025)
• Concept-Guided Backdoor Attack on Vision Language Models
  di: Shen, Haoyu, et al.
  Pubblicazione: (2025)
• Your Agent Can Defend Itself against Backdoor Attacks
  di: Changjiang, Li, et al.
  Pubblicazione: (2025)
• Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
  di: Obioma, Chibueze Peace, et al.
  Pubblicazione: (2025)