A researcher has created a "two-factor authentication" system for facial recognition that uses
The system is called simultaneous two-factoridentity verification (C2FIV). It requires the user to record a short video of the face. You also need to read a certain phrase out loud. Then you need to download the video to your device for authorization. The system will then require both the face itself and a certain gesture to be activated.
C2FIV reportedly relies on a neural network that was trained on a dataset of 8,000 videos. People on roller skates winked, smiled, or raised their eyebrows.
The system should be more reliable. As its creator says, even if someone gains access to your device, they will never know which gesture you use to unlock.