PulseAugur
中
实时 12:03:58
English(EN) SWAN: Semantic Watermarking with Abstract Meaning Representation

SWAN框架将水印嵌入语义结构中,实现鲁棒的文本溯源

研究人员开发了SWAN,一个使用抽象语义表示(AMR)将水印嵌入句子语义结构的新框架。与以往改变词语选择的方法不同,SWAN将签名直接编码到语义表示中,使其能够抵抗释义。这种无需训练的方法使用LLM提示进行注入,并使用AMR解析器进行检测,取得了最先进的性能,并在抵抗释义方面将检测AUC提高了多达13.9个百分点。 AI

影响 引入了一种更鲁棒的文本溯源验证方法,即使在修改后也能帮助检测AI生成的内容。

排序理由 该集群包含一篇详细介绍新型语义水印框架的学术论文。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

SWAN框架将水印嵌入语义结构中,实现鲁棒的文本溯源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含一篇详细介绍新型语义水印框架的学术论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
148 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Ziping Ye, Gourab Dey, Christos Christodoulopoulos, Charith Peris, Anil Ramakrishna, Weitong Ruan, Aram Galstyan, Kai-Wei Chang, Rahul Gupta, Ninareh Mehrabi ·

    SWAN:基于抽象语义表示的语义水印

    arXiv:2605.04305v1 Announce Type: new Abstract: We introduce SWAN (Semantic Watermarking with Abstract Meaning Representation), a novel framework that embeds watermark signatures into the semantic structure of a sentence using Abstract Meaning Representation (AMR). In contrast to…

  2. arXiv cs.CL TIER_1 English(EN) · Ninareh Mehrabi ·

    SWAN:基于抽象语义表示的语义水印

    We introduce SWAN (Semantic Watermarking with Abstract Meaning Representation), a novel framework that embeds watermark signatures into the semantic structure of a sentence using Abstract Meaning Representation (AMR). In contrast to existing watermarking methods, which typically …