Watermark and provenance signals
AI watermark detector
Check whether content has available AI watermark, provenance, or metadata signals and learn what remains publicly unverifiable.
Run a signal check
No detector model loads until you press Check.
Current support
Public watermark detection is provider-specific. AI Detect separates visible provenance from probabilistic text signals.
What this checks
- Provider watermark support is tracked in a structured registry.
- C2PA metadata can identify provenance when present in supported files.
- Statistical text classifiers are treated as risk signals, not proof.
What this does not prove
- Private provider watermark algorithms may not be publicly detectable.
- Watermark metadata can be stripped during copy, export, or platform processing.
- Text-only watermark checks depend on the provider and generation pipeline.
FAQ
- Can this prove whether content was written by AI?
No. AI Detect reports signals such as provenance metadata, watermark support status, and statistical text risk. It does not claim legal or authorship proof.
- Does text leave my browser during a local check?
Browser-default checks run local text features and provenance checks after you press Check. Server enhanced checks are separate and will be labelled before use.
- Why can a result be unknown?
Many providers do not expose public watermark detectors, and metadata can be absent or stripped. Unknown is a valid result when no reliable public signal exists.
Provider registry
Current watermark support
| Provider | Text watermark | Detection | File provenance | Tamper risk | Updated | Sources |
|---|---|---|---|---|---|---|
| Anthropic / Claudeanthropic, claude, claude-sonnet, claude-opus | plannedSynthID-Text-style statistical watermark | plannedAnthropic has described Claude text watermarking and says a detection API is planned, but no public Claude verification adapter is connected yet. | C2PAsupported_when_present | weak against rewriteClaude text watermarking is described as a statistical wording signal. Substantial rewriting can weaken it; C2PA file credentials are a separate metadata/provenance layer that can be stripped or lost. | 2026-08-17 | |
| Google / Geminigoogle, gemini, synthid | researchSynthID Text | availableSynthID Text is documented for compatible generation pipelines, but it is not a universal detector for arbitrary pasted text. | n/a | weak against rewriteSynthID-class text signals are statistical and should be treated as probabilistic. Media and file provenance can involve separate metadata or pixel-domain marks with different removal risks. | 2026-08-12 |
Workflow upgrade
Need repeatable reviews?
Move from one-off checks to saved reports, batch review, and API-ready signal records when the workflow needs it.