Meet Atlas Live: liveness detection with no gesture required
Atlas

Biometrics Available

Atlas Live

Passive liveness: detects replayed screens, printed photos and reused document portraits.

Request a demo Start in the sandbox

Access by invitation: no account yet? Ask for your sandbox workspace.

What it checks

A real person, in front of the camera.

Atlas Live analyses the selfie without asking the customer to move, and flags known presentation attempts.

  • Passive liveness

    No movement required: a single selfie is enough, and the flow stays short.

  • Replayed screen

    A photo or video shown on another screen is detected, and the check fails.

  • Printed photo

    A printed or photocopied face held up to the camera is flagged for review.

  • Reused document portrait

    The document portrait presented as a selfie is recognised, and the check fails.

  • Capture quality

    No face, several faces or a weak image: the customer is guided and the file is flagged.

  • Deepfakes and injection

    Coming soon

    Detection of generated faces and injected video streams.

How it works

One selfie, no gestures.

  1. 1 The customer takes a selfie In the hosted flow, with an oval to guide them.
  2. 2 Atlas analyses the image Liveness score and attack signals computed on the capture.
  3. 3 The result follows your rules Confirmed attack: fail. Doubt: human review. Otherwise, the check passes.

Presentation checks

  • Replayed screen not detected
  • Printed photo not detected
  • Document portrait reused not detected
  • One face only yes
  • Deepfakes and injection Coming soon

Liveness Passed

Illustrated portrait. Passive detection: the customer is asked for no gesture.

For developers

Reasons, not just a score.

The liveness check returns its status and the reasons detected, the same in the API and in the webhooks.

Developer guide Start in the sandbox

Request

curl https://verify.atlasidv.com/v1/verifications/7f3c9a2e-… \
  -H "Authorization: Bearer atlas_sk_sandbox_…"

Response 200 OK 

{
  "status": "needs_review",
  "reason_codes": ["liveness_screen_replay"],
  "checks": [
    {
      "type": "liveness",
      "status": "failed"
    }
  ]
}

Take the next step

Try Atlas Live on your own flows.

A demo on your real cases, then a sandbox space with synthetic identities to integrate without any real data.

Request a demo Start in the sandbox