Bypassing LLM Watermarks with Color-Aware Substitutions

arXiv:2403.14719v1 Announce Type: cross
Abstract: Watermarking approaches are proposed to identify if text being circulated is human or large language model (LLM) generated. The state-of-the-art watermarking strategy of Kirchenbauer et al. (2023a) biases the LLM to generate specific (``green'') tokens. However, determining the robustness of this watermarking method is an open problem. Existing attack methods fail to evade detection for longer text segments. We overcome this limitation, and propose {\em Self Color Testing-based Substitution (SCTS)}, the first ``color-aware'' attack. SCTS …

abstract art arxiv biases color cs.cr cs.cv cs.lg generate generated green however human identify language language model large language large language model llm robustness state strategy text tokens type watermarking watermarks