API Marketplace

Solutions

Resources

Our Company

Book a Demo

← Back to Glossary

Liveness Detection

Overview

Liveness detection determines whether a biometric sample comes from a live person present at capture time, not a spoof (photo, video, silicone mask, synthetic stream). It complements face/voice matching and is foundational for remote onboarding and step-up authentication. Methods include active challenges (blink, head turns), passive signals (texture, reflectance, micro-movements), depth sensing, and sensor- or software-based anti-spoofing aligned to ISO/IEC 30107-3 testing.

Strong programs evaluate PAD performance (attack presentation error), monitor field drift, and combine liveness with secure capture, device attestation, and quality gates. Thresholds vary by risk: higher assurance for account opening or high-value actions. Clear UX guidance improves success rates without weakening defenses.Documenting test results, attack coverage, and operational metrics builds regulator confidence and reduces successful impersonation attempts across channels and devices.

Stay ahead of risk with Signzy

Explore tools that help you onboard, monitor, and verify with confidence

Liveness Check

Verify real users using biometric liveness detection and selfie checks to prevent spoofing and deepfake attacks during onboarding.

Biometric Verification

Authenticate users with facial, fingerprint, and liveness biometrics powered by AI to prevent identity spoofing and fraud.

One Touch KYC

Launch global KYC flows with built-in document OCR, liveness checks, deepfake detection, and AML, all through a single, customizable dashboard.

Related Terms

Presentation Attack Detection (PAD)

Face Match

Video Liveness Check

FAQ

How is liveness different from PAD?

Liveness proves a real, present user; PAD targets known spoof artifacts. They’re complementary, most robust systems implement both to raise assurance against varied attacks.

What methods work best?

Multi-signal approaches (passive cues + randomized prompts + depth) improve robustness. Choice depends on device capabilities, risk level, and user experience goals.

How do we measure effectiveness?

Track false accept/reject, attack error rates, and recapture rates in production. Re-test after model or SDK updates to prevent silent regressions.

Can liveness be bypassed?

Advanced spoofs and injection attacks evolve. Secure capture pipelines, cryptographic challenges, and continuous model retraining help sustain resilience.