Researchers at Tel Aviv University Claim to Bypass Facial Recognition with Master Face

The team claims that facial recognition is vulnerable. However, I could not find any reference to specific challenges to facial recognition techniques used by iPhone or Android so I can’t yet determine how much of a threat this really is after a quick scan of the study. iPhone facial ID capture 30,000 invisible infrared dots which are then encrypted. I don’t see this trick bypassing iPhone. Maybe it will bypass the less secure Samsung facial recognition technology. If you want to learn more about StyleGAN Face Image Generation (FG) and their techniques you can read more in the study PDF below after reading the article. The PDF is not easy reading for the newbie.

Indeed, computer scientists at Tel Aviv University in Israel say they have discovered a way to bypass a large percentage of facial recognition systems by basically faking your face. The team calls this method the “master face” (like a “master key,” harhar), which uses artificial intelligence technologies to create a facial template—one that can consistently juke and unlock identity verification systems.

“Our results imply that face-based authentication is extremely vulnerable, even if there is no information on the target identity,” researchers write in their study. “In order to provide a more secure solution for face recognition systems, anti-spoofing methods are usually applied. Our method might be combined with additional existing methods to bypass such defenses,” they add.

According to the study, the vulnerability being exploited here is the fact that facial recognition systems use broad sets of markers to identify specific individuals. By creating facial templates that match many of those markers, a sort of omni-face can be created that is capable of fooling a high percentage of security systems. In essence, the attack is successful because it generates “faces that are similar to a large portion of the population.”


Gizmodo has the story.

Study here.

Privacy Policy | Terms of Service