Trust and safety

Use case

Content platforms need to triage user-uploaded images at volume without false-accusing real people. ChronoVerify returns a deterministic, signed verdict you can wire into an automated review pipeline.

The workflow

Verify in the pipeline. Call the API as part of your ingestion or report-handling flow.
Read provenance and consistency. Validate Content Credentials, check capture time and metadata consistency.
Route by verdict. Send manipulation_indicated and metadata_anomaly to human moderators; keep a signed record for appeals.

Which verdicts matter

The deterministic verdict and confidence are designed to drop into an automated decision pipeline. Bias toward routing flags to humans, and keep the signed report for an audit trail and appeals.

What this can and cannot tell you

Pixel forensics are probabilistic and degrade on recompressed images, so ChronoVerify is deliberately conservative to avoid false accusations. A verdict is triage, never a sole basis for an action against a user or a determination about a person.

One call

curl -X POST https://chronoverify.com/v1/verify \
  -H "Authorization: Bearer cv_live_..." \
  -F "url=https://cdn.example.com/upload.jpg"

Omit the Authorization header to use the free, rate-limited public path. Full field reference is on the method and API page.

Common questions

Why deterministic instead of a probability score?

A deterministic, signed verdict can be wired into an auditable automated decision and reproduced later; a black-box probability cannot. ChronoVerify gives you the verdict plus every signal behind it.

Can it mark AI-generated content for Article 50?

It reads and validates C2PA Content Credentials, the machine-readable marking Article 50 relies on. It is the verification and audit layer, not an AI-generation detector, and not legal advice.

See a verdict on a real photo.

Try the free verifier