Liveness Detection and Anti-Spoofing

Liveness – Anti Spoofing, Daon

Chances are, your password is already compromised, your social security number is for sale on the dark web, and the answers to your “secret” questions are posted on social media.

But what about your biometrics—your face and your voice? Can they be compromised?

The simple answer is no, your biometrics can’t be compromised, because they aren’t secrets.

But this simple answer makes a rather large assumption—that your biometric system can reliably differentiate between the real you and some imposter with a picture of your face or a recording of your voice. We call this detecting “liveness,” and no—not every biometric system can do it well.

Like all technologies, certain liveness detection techniques and anti spoofing algorithms are better than others. And, increasingly, this is becoming a key consideration when evaluating and choosing among competing biometric solutions.

HOW DOES DAON USE LIVENESS DETECTION FOR BIOMETRIC ANTI-SPOOFING?

Daon’s IdentityX deploys several Presentation Attack Detection (PAD) algorithms to combat spoofing by detecting genuine live users (liveness detection).

These liveness detection/anti spoofing techniques are used in conjunction with our authentication algorithms and can be performed either actively (i.e., done with the user’s active participation) or passively.

Presentation attacks can be further minimized by combining multiple active liveness challenges with passive techniques. For example, a user could be asked to perform a combination of active liveness challenges such as nodding or shaking their head, moving the capture camera, moving or blinking their eyes, smiling or speaking. Simultaneously, passive techniques (detecting reflections, screen bezel edges, unusual textures and colors in the face region, lack of face micro-movements or audio artifacts) could be used to further corroborate the liveness of the user.

As with biometric matching, liveness detection algorithms are probabilistic; bona fide attempts may be incorrectly classified as presentation attacks and vice versa. As such, IdentityX allows you to custom tune these operational thresholds, so you can avoid inconveniencing your legitimate users while minimizing the likelihood of a presentation attack.

 

Daon offers a portfolio of best-in-class tested PAD approaches, incorporating algorithms that can be used separately or together; each approach is carefully selected to provide appropriate protection for specific authentication scenarios. As attackers and software become more sophisticated, we continue to develop and evaluate new techniques to help keep ahead of these threats. Find out more about the R&D work of the Daon Biometric Research Lab. Or, learn more about IdentityX and Multi Factor Authentication.