Anthropic 详解 Claude 文本隐形水印机制 Anthropic Explains How Claude's Invisible Text Watermarks Will Work

精读摘要

Anthropic 澄清了为 Claude 生成文本添加隐形水印的方案：采用 Google DeepMind 开源的 SynthID-Text 技术路线，通过词语概率分布嵌入可检测的标记模式。配合对 Claude 处理图像的 C2PA 支持，这套机制是为了满足欧盟《AI 法案》对合成内容的透明度要求。 Anthropic clarified that Claude's text watermarking is a version of SynthID-Text, Google DeepMind's open-source technique that creates detectable patterns via wording probabilities. Alongside C2PA support for Claude-processed images, the mechanism aims to meet the EU AI Act's transparency requirements for synthetic content.