Anthropic explains how Claude’s invisible text watermarks will work
infonewsLLM-Specific
policysecurity
Source: The Verge (AI)August 17, 2026
Summary
Anthropic is adding invisible watermarks to text generated by Claude, its AI assistant, to follow European Union rules requiring AI-generated content to be marked. The watermarks use SynthID-Text (an open-source technology from Google DeepMind that creates detectable patterns in text by adjusting word choices), and this feature is being added alongside image watermarking to comply with the EU's AI Act.
Classification
Attack SophisticationModerate
Impact (CIA+S)
integrity
AI Component TargetedModel
Affected Vendors
Anthropic
Related Issues
Monthly digest — independent AI security research
Original source: https://www.theverge.com/ai-artificial-intelligence/980869/anthropic-claude-watermarks-synthid-text-system
First tracked: August 17, 2026 at 08:01 AM
Classified by LLM (prompt v3) · confidence: 85%