English(EN) Constructing Budgeted KGW Evasion through Token-Event Evidence Replacement

通过令牌事件替换规避LLM水印的新方法

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 05:00

研究人员开发了一种通过替换令牌事件证据来规避大型语言模型中水印的方法。该技术涉及使用普通的短语重写，并测量全局令牌编辑距离来移除原始评分令牌对。研究发现，在设定的预算内，很大一部分最初检测到的来源可以被重写以规避检测，尽管更简单的重写方法没有显示出明显的优势。 AI

影响这项研究突显了LLM水印技术潜在的漏洞，表明需要更强大的检测方法。

排序理由详细介绍一种规避LLM水印新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 41 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍一种规避LLM水印新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Hongliang Liu · 2026-11-04 05:00

通过令牌事件证据替换构建预算式KGW规避

arXiv:2611.00726v1 Announce Type: new Abstract: KGW watermarks bias sampling to accumulate keyed detection evidence. We construct budgeted evasion through token-event evidence replacement using ordinary phrase rewrites. Our construction jointly selects compositions of LLM-propose…