RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience

Documenti analoghi

• RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
  di: Huang, Hanbo, et al.
  Pubblicazione: (2025)
• Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
  di: Shen, Huanming, et al.
  Pubblicazione: (2025)
• Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
  di: An, Li, et al.
  Pubblicazione: (2025)
• A Reinforcement Learning Framework for Robust and Secure LLM Watermarking
  di: An, Li, et al.
  Pubblicazione: (2025)
• Watermarking LLM Agent Trajectories
  di: Meng, Wenlong, et al.
  Pubblicazione: (2026)