Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack

Documenti analoghi

• Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)
• Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2025)
• Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)
• Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)
• Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2025)