ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration
Researchers have proposed ChainMark, a watermarking method for text generated by large language models (LLMs) that does not require access to the underlying model. ChainMark uses keyed hashing to partition vocabulary and enforces Markov transitions, enabling detection with closed-form calibration of false positive rates. The approach demonstrates robustness against translation and substitution attacks and outperforms prior methods in empirical tests.
Why it matters: ChainMark provides a practical and theoretically grounded solution for marking synthetic text, addressing regulatory needs for reliable watermarking without requiring model access.
Full story at: arXiv Cryptography and Security ↗