arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.22007math.STcs.CLcs.CRcs.LGstat.MLstat.TH
收藏

语言水印的最优检测与伪随机碰撞

Optimal Detection for Language Watermarks with Pseudorandom Collision

University of Pennsylvania(宾夕法尼亚大学);Yale University(耶鲁大学)

T. Tony Cai, Xiang Li, Qi Long, Weijie J. Su, Garrett G. Wen

AI总结:

本文提出了一种基于最小单位的统计框架,用于在不完美伪随机性下优化语言水印检测,通过理论分析和实验验证提升了检测能力并严格控制类型I错误。

摘要:

文本水印在确保大型语言模型(LLM)输出的可追溯性和问责制以及防止滥用方面起着至关重要的作用。虽然前景广阔,但大多数现有方法假设了完美的伪随机性。在实践中,生成文本中的重复性会引发碰撞,从而产生结构依赖性,这会破坏类型I错误控制并使标准分析失效。我们介绍了一个统计框架,通过层次化的双层分区来捕捉这种结构。其核心概念是

英文摘要:

Text watermarking plays a crucial role in ensuring the traceability and accountability of large language model (LLM) outputs and mitigating misuse. While promising, most existing methods assume perfect pseudorandomness. In practice, repetition in generated text induces collisions that create structured dependence, compromising Type I error control and invalidating standard analyses. We introduce a statistical framework that captures this structure through a hierarchical two-layer partition. At its core is the concept of minimal units -- the smallest groups treatable as independent across units while permitting dependence within. Using minimal units, we define a non-asymptotic efficiency measure and cast watermark detection as a minimax hypothesis testing problem. Applied to Gumbel-max and inverse-transform watermarks, our framework produces closed-form optimal rules. It explains why discarding repeated statistics often improves performance and shows that within-unit dependence must be addressed unless degenerate. Both theory and experiments confirm improved detection power with rigorous Type I error control. These results provide the first principled foundation for watermark detection under imperfect pseudorandomness, offering both theoretical insight and practical guidance for reliable tracing of model outputs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑