Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink

Documenti analoghi

• Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation
  di: Liu, Guozhi, et al.
  Pubblicazione: (2024)
• Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
  di: Liu, Guozhi, et al.
  Pubblicazione: (2025)
• Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
  di: Wang, Yibo, et al.
  Pubblicazione: (2025)
• Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)
• Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)