QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs

Documenti analoghi

• WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness
  di: Huang, Baizhou, et al.
  Pubblicazione: (2024)
• $B^4$: A Black-Box Scrubbing Attack on LLM Watermarks
  di: Huang, Baizhou, et al.
  Pubblicazione: (2024)
• Towards Codable Watermarking for Injecting Multi-bits Information to LLMs
  di: Wang, Lean, et al.
  Pubblicazione: (2023)
• Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency
  di: Huang, Baizhou, et al.
  Pubblicazione: (2023)
• Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
  di: Shen, Huanming, et al.
  Pubblicazione: (2025)