From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Yidan, Ren, Yubing, Cao, Yanan, Fang, Binxing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909611925176320
author Wang, Yidan
Ren, Yubing
Cao, Yanan
Fang, Binxing
author_facet Wang, Yidan
Ren, Yubing
Cao, Yanan
Fang, Binxing
contents The rise of Large Language Models (LLMs) has heightened concerns about the misuse of AI-generated text, making watermarking a promising solution. Mainstream watermarking schemes for LLMs fall into two categories: logits-based and sampling-based. However, current schemes entail trade-offs among robustness, text quality, and security. To mitigate this, we integrate logits-based and sampling-based schemes, harnessing their respective strengths to achieve synergy. In this paper, we propose a versatile symbiotic watermarking framework with three strategies: serial, parallel, and hybrid. The hybrid framework adaptively embeds watermarks using token entropy and semantic entropy, optimizing the balance between detectability, robustness, text quality, and security. Furthermore, we validate our approach through comprehensive experiments on various datasets and models. Experimental results indicate that our method outperforms existing baselines and achieves state-of-the-art (SOTA) performance. We believe this framework provides novel insights into diverse watermarking paradigms. Our code is available at https://github.com/redwyd/SymMark.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
Wang, Yidan
Ren, Yubing
Cao, Yanan
Fang, Binxing
Computation and Language
Cryptography and Security
The rise of Large Language Models (LLMs) has heightened concerns about the misuse of AI-generated text, making watermarking a promising solution. Mainstream watermarking schemes for LLMs fall into two categories: logits-based and sampling-based. However, current schemes entail trade-offs among robustness, text quality, and security. To mitigate this, we integrate logits-based and sampling-based schemes, harnessing their respective strengths to achieve synergy. In this paper, we propose a versatile symbiotic watermarking framework with three strategies: serial, parallel, and hybrid. The hybrid framework adaptively embeds watermarks using token entropy and semantic entropy, optimizing the balance between detectability, robustness, text quality, and security. Furthermore, we validate our approach through comprehensive experiments on various datasets and models. Experimental results indicate that our method outperforms existing baselines and achieves state-of-the-art (SOTA) performance. We believe this framework provides novel insights into diverse watermarking paradigms. Our code is available at https://github.com/redwyd/SymMark.
title From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
topic Computation and Language
Cryptography and Security
url https://arxiv.org/abs/2505.09924