Detect spoofing without user action.
Confirm a real, live person is in front of the camera from a single selfie or video frame — no blinks, head turns, or prompts required. Passive liveness scores every capture in real time, catching printed photos, replayed video, and masks before they reach your onboarding or authentication flow.
Zero-prompt detection
Runs on a single passive frame with no challenge-response gestures, keeping onboarding and login fast while still catching spoofed captures.
Multi-attack spoof classification
Flags the specific attack vector — printed photo, screen replay, or mask — not just a pass/fail signal, so downstream teams know what they're looking at.
Confidence-scored decisions
Every check returns a calibrated liveness score alongside the verdict, so you can tune thresholds per risk tier instead of trusting a black-box boolean.
A single frame is enough — the model reads texture, depth cues, and reflections for signs of tampering, then classifies exactly which attack it caught (printed photo, screen replay, mask) instead of returning a bare pass/fail.
Get API access in days, or bring us in to run the full workflow for you — sovereignty by design at every step.