Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning

Documenti analoghi

• Safety Layers in Aligned Large Language Models: The Key to LLM Security
  di: Li, Shen, et al.
  Pubblicazione: (2024)
• Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
  di: Kong, Cong, et al.
  Pubblicazione: (2024)
• SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking
  di: Yang, Wenyuan, et al.
  Pubblicazione: (2025)
• Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
  di: Liu, Guozhi, et al.
  Pubblicazione: (2025)
• I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
  di: Panzade, Prajwal, et al.
  Pubblicazione: (2024)