Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Documenti analoghi

• Task-Distributionally Robust Data-Free Meta-Learning
  di: Hu, Zixuan, et al.
  Pubblicazione: (2023)
• Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
  di: Hu, Zixuan, et al.
  Pubblicazione: (2024)
• Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
  di: Hu, Zixuan, et al.
  Pubblicazione: (2025)
• Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
  di: Hu, Zixuan, et al.
  Pubblicazione: (2023)
• Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
  di: Huang, Tiansheng, et al.
  Pubblicazione: (2024)