'Master Face': Researchers Say They've Found a Wildly Successful Bypass for Face Recognition Tech

[Nevilledog]

Link to tweet

Tweet text:
hypervisible dot pdf
@hypervisible
Researchers claim they are able to generate a “master face” template that can fool a large number of biometric authentication systems.

“Master face” 🤔

'Master Face': Researchers Say They've Found a Wildly Successful Bypass for Face Recognition Tech
A group of researchers says that artificial intelligence can be used to trick most biometric face scanners.
gizmodo.com
5:24 AM · Aug 5, 2021

https://gizmodo.com/master-face-researchers-say-theyve-found-a-wildly-succ-1847420710

In addition to helping police arrest the wrong person or monitor how often you visit the Gap, facial recognition is increasingly used by companies as a routine security procedure: it’s a way to unlock your phone or log into social media, for example. This practice comes with an exchange of privacy for the promise of comfort and security but, according to a recent study, that promise is basically bullshit.

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.”

*snip*

[unblock]

1. I'm disappointed that it's not Kevin bacon.

[chowder66]

2. Now that's friggin' funny. nt

[EYESORE 9001]

3. Face in the picture looks like Mao