融合两种水印技术，实现鲁棒性与文本质量的双赢。
From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
- 将基于概率和采样的水印方法结合，发挥各自优势。
- 混合策略根据熵值自适应嵌入，平衡检测率与生成质量。
- 在多个模型和数据集上验证，性能优于现有方法。
大型语言模型（LLMs）的兴起加剧了人工智能生成文本被滥用的风险，水印技术成为应对这一问题的有前景方案。主流水印方法分为基于逻辑值（logits-based）和基于采样（sampling-based）两类，但现有方案在鲁棒性、文本质量和安全性之间存在权衡。为此，本文提出一种灵活的共生水印框架，包含串行、并行和混合三种策略。其中，混合框架利用词元熵和语义熵自适应嵌入水印，优化了可检测性、鲁棒性、文本质量与安全性之间的平衡。我们在多种数据集和模型上进行了全面实验，结果表明该方法优于现有基线，达到当前最优（SOTA）水平。本工作为多元水印范式提供了新思路。代码已公开于 https://github.com/redwyd/SymMark。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。