Demographic bias in facial liveness detection: impact, measurement, and mitigation

AI-powered facial liveness detection algorithms can introduce bias the same way matching algorithms can, causing mobile banking services to be less accessible for individuals based on their demographics. But the issue has garnered little attention until now.

In response to the risk, ID R&D commissioned the first-ever independent evaluation of a facial liveness detection algorithm for demographic bias. The test was performed and recently completed by BixeLab, a NIST NVLAP-accredited biometrics laboratory.

ID R&D and BixeLab shared their thoughts and experiences on the topic in a webinar hosted and moderated by Biometric Update.

Fill out the form below to watch the webinar.

View Webinar

Please fill out the following brief form in order to access this webinar.

Article Topics

biometric liveness detection  |  biometric-bias  |  biometrics  |  BixeLab  |  face biometrics  |  ID R&D  |  webinar