Glossary term
Presentation Attack
Definition
A presentation attack is an attempt to defeat biometric verification by presenting falsified evidence to the sensor: a printed photo, a screen replay, a silicone mask, or a deepfake displayed to the camera. It is the "in front of the camera" attack class, standardized in ISO/IEC 30107 alongside presentation attack detection (PAD).
Why it matters for financial institutions
Every remote KYC flow, selfie check, and video authorization is a sensor an attacker can present to. As deepfake quality improves, presentation attacks have shifted from crude printed photos to high-fidelity synthetic faces and voices that pass casual PAD checks — putting onboarding controls and their regulatory obligations (CIP, CDD) at risk.
How FalsiFind addresses it
FalsiFind detects the synthetic-generation artifacts in presented media — texture and frequency anomalies in faces, synthesis artifacts in voices — providing a PAD-complementary signal that stays effective as presentation tools improve.