R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models

Documenti analoghi

• Generative Model Watermarking Suppressing High-Frequency Artifacts
  di: Zhang, Li, et al.
  Pubblicazione: (2023)
• Yet Another Watermark for Large Language Models
  di: Bao, Siyuan, et al.
  Pubblicazione: (2025)
• Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings
  di: Zhao, Xiangyu, et al.
  Pubblicazione: (2024)
• Robust and Imperceptible Black-box DNN Watermarking Based on Fourier Perturbation Analysis and Frequency Sensitivity Clustering
  di: Liu, Yong, et al.
  Pubblicazione: (2022)
• CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models
  di: Ren, Zhenzhen, et al.
  Pubblicazione: (2025)