Microsoft introduces Selfie Authentication using Face Check System

The Face API from Azure AI Vision by Microsoft is utilized for facial recognition and detection. It is also capable of performing a validation of “liveness” to mitigate the risk of fraudulent attempts using static images or 2D videos, thereby making it difficult for deepfakes to succeed.

Organizations have the flexibility to select the confidence level required for approving a Face Check login. A higher threshold for the confidence score reduces the chances of false verification of an impersonator by Face Check. By default, the system operates at a 50% match rate, translating to a 1 in 100,000 probability of a false positive; at 90%, the probability decreases to one in a billion, as stated by Microsoft. (Furthermore, an elevated confidence score prerequisite also raises the probability of genuine login attempts being declined.)

Any alterations in the user’s appearance in comparison to the authenticated photo, such as a different hairstyle, or discrepancies in the background setting, like lighting variations, can affect the matching score.

About Author

AndyC

Andy Curtis is an award-winning security consultant, researcher and public speaker. He has been working in the computer security industry since the early 1990s, having been employed by state and federal government, leading healthcare and banking providers across three continents. He has given talks about computer security for some of the world’s largest companies, worked with law enforcement agencies on investigations into hacking groups, and is a regular voice on TV and radio explaining IT security threats.

See author's posts