Microsoft Launches Face Check Selfie Verification System – Computerworld

Microsoft’s Azure AI Vision Face API is used to power facial detection and recognition. The software can also perform a “liveness” check that helps prevent a static photo or 2D video from being used to fool the verification system, Microsoft said, so deepfakes shouldn’t be effective.

Customer organizations can choose the level of trust required to accept a Face Check login attempt. The higher the trust score threshold, the less likely Face Check is to incorrectly verify an impersonator. The default score is a 50% match, which equates to a one-in-100,000 chance of receiving a false positive; at 90%, the chance is one in a billion, Microsoft said. (Requiring a higher trust score also increases the likelihood that a legitimate login attempt will be rejected.)

Changes in a user’s appearance compared to their verified photo — a different hairstyle, for example — can lower their match score, as can differences in their surroundings, such as lighting.