arXiv cs.CL· Yupeng Qiu, Han Fang, Ee-Chien Chang·· 12 小时前AI 评分29
ClockMark：面向大语言模型的自适应、依赖宿主的水印方法
ClockMark: Adaptive and Host-Dependent Watermarking for Large Language Models
AI 导读
ClockMark 是一种面向 LLM 流式生成的水印嵌入框架，主张嵌入应自适应保留先前采样状态、并依赖当前 LLM 分布约束 token 选择与状态更新，同时将完整载荷嵌入每个水印 token。理论上证明其保持原始 LLM 序列分布，实验中对比 12 个基线，在文本编辑场景下比特准确率最高提升 16.08 个百分点。
正文 · 原文
Abstract:Large language model (LLM) watermarking operates on the next-token distribution that evolves during generation. In streaming generation, each sampled token becomes part of the text and affects subsequent distributions. Embedding therefore proceeds with a changing host, unlike classical watermarking, which adapts embedding to an existing host signal. To accommodate this difference, we formulate a novel embedding framework for LLM watermarking based on two principles. We first argue that embedding should be adaptive, retaining the state of previous sampling decisions to better guide subsequent choices. We further argue that embedding should be host-dependent, using the current LLM distribution to constrain both token selection and state updates. Guided by these principles and the two requirements of distribution preservation and robustness to text editing, we propose ClockMark. It combines adaptive and host-dependent embedding with message spreading, embedding the full payload in each watermarked token. Theoretically, we prove that ClockMark preserves the original LLM sequence distribution, thereby maintaining generation quality. Empirically, extensive experiments against 12 baselines demonstrate improved robustness to text editing, with gains of up to 16.08 percentage points in bit accuracy over the strongest tested baseline.
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.27079 [cs.LG] |
| (or arXiv:2610.27079v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27079 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yupeng Qiu [view email]
[v1]
Mon, 19 Oct 2026 18:00:03 UTC (1,988 KB)
来源：arXiv cs.CL · arxiv.org