BiCoT embeds watermarks into the internal geometry of Chain-of-Thought reasoning traces in LLMs via private signature subspace alignment and introduces Robust Subspace Registration for black-box verification under attacks.
Holmes: Towards effective and harmless model ownership verification to personalized large vision models via decoupling common features
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
BiCoT embeds watermarks into the internal geometry of Chain-of-Thought reasoning traces in LLMs via private signature subspace alignment and introduces Robust Subspace Registration for black-box verification under attacks.