提出自锚定水印框架，抗段落级改写攻击，鲁棒性提升超30%。
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
- 通过语义空间中独立于顺序的绿色区域，消除句序依赖
- 在段落改写攻击下达到90.2%查准率，优于前代方法30%以上
- 适合需高鲁棒性文本水印的生成模型应用
语义级水印（SWM）通过将句子作为基本单元提升对文本修改的鲁棒性，但面对段落级改写攻击仍难应对，因此类攻击会全局打乱水印信号。本文提出SAMark，一种自锚定水印框架，通过在语义空间中建立与步骤无关的绿色区域，消除对句序的依赖。为增强可检测性，引入多通道双曲评分机制，放大水印信号并抑制弱对齐候选噪声。进一步提出多样性感知过滤策略，结合硬过滤与软正则化，超越简单n-gram重复过滤，缓解语义冗余。实验表明，SAMark在典型段落级改写攻击下实现高达90.2%的TP@FP1%，平均优于最强基线超过30%，同时保持生成质量与无水印文本相当，突破了以往方法的鲁棒性-质量权衡瓶颈。代码将公开于[此链接](https://github.com/Z1zs/SAMark)。
原文摘要 · Abstract (English)
Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remains difficult because such attacks globally disrupt watermark signals by changing sentence order. In this work, we propose SAMark, a self-anchored watermarking framework that removes the dependency on sentence order by establishing a step-independent green region in semantic space. To improve detectability, we introduce a multi-channel hyperbolic scoring mechanism that amplifies watermark signals while suppressing noise from weakly aligned candidates. We further propose a diversity-aware filtering strategy that combines hard filtering with soft regularization, extending beyond simple n-gram repetition filters to address semantic redundancy. Experimental results show that SAMark achieves up to 90.2% TP@FP1% under typical paragraph-level paraphrasing attacks, outperforming the strongest prior baseline by more than 30% on average, while maintaining generation quality competitive with unwatermarked text and breaking the robustness-quality trade-off that limits prior methods. Our code will be released at [this URL](https://github.com/Z1zs/SAMark).
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。