Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs

概要

arXiv:2605.07481v1 Announce Type: cross Abstract: In this paper, we investigate the recent state-of-the-art schemes for watermarking large language models (LLMs) outputs. These techniques are claimed to be robust, scalable and production-grade, aimed at promoting responsible usage of LLMs. We analy…