CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yu, Liu, Shuliang, Yang, Xu, Hu, Xuming
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909821599481856
author Zhang, Yu
Liu, Shuliang
Yang, Xu
Hu, Xuming
author_facet Zhang, Yu
Liu, Shuliang
Yang, Xu
Hu, Xuming
contents Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially in low-entropy scenarios where performance needs improvement. Existing methods that rely on entropy thresholds often require significant computational resources for tuning and demonstrate poor adaptability to unknown or cross-task generation scenarios. We propose \textbf{C}ontext-\textbf{A}ware \textbf{T}hreshold watermarking ($\myalgo$), a novel framework that dynamically adjusts watermarking intensity based on real-time semantic context. $\myalgo$ partitions text generation into semantic states using logits clustering, establishing context-aware entropy thresholds that preserve fidelity in structured content while embedding robust watermarks. Crucially, it requires no pre-defined thresholds or task-specific tuning. Experiments show $\myalgo$ improves text quality in cross-tasks without sacrificing detection accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02342
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models
Zhang, Yu
Liu, Shuliang
Yang, Xu
Hu, Xuming
Cryptography and Security
Artificial Intelligence
Computation and Language
Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially in low-entropy scenarios where performance needs improvement. Existing methods that rely on entropy thresholds often require significant computational resources for tuning and demonstrate poor adaptability to unknown or cross-task generation scenarios. We propose \textbf{C}ontext-\textbf{A}ware \textbf{T}hreshold watermarking ($\myalgo$), a novel framework that dynamically adjusts watermarking intensity based on real-time semantic context. $\myalgo$ partitions text generation into semantic states using logits clustering, establishing context-aware entropy thresholds that preserve fidelity in structured content while embedding robust watermarks. Crucially, it requires no pre-defined thresholds or task-specific tuning. Experiments show $\myalgo$ improves text quality in cross-tasks without sacrificing detection accuracy.
title CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models
topic Cryptography and Security
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.02342