Professor D.J. Lee, a scientist at Brigham Young University, developed a new AI system that makes biometric authentication more secure by analyzing facial movements.
To do so, the users have to record a video of themselves making a unique facial motion and the AI system will use this to recognize particular features and movements of the person. Thus, when the user wants to access their phone, the system will check that their face matches the recorded data.
This new AI tech is called Concurrent Two-Factor Identity Verification (C2FIV) and aims to offer users a safer verification method than current biometric identifiers. This will also make sure that the identity verification process is intentional.
During a preliminary study, the neural network was trained on 8,000 clips of 50 subjects making various facial movements including smiling, blinking, and raising their eyebrows. The AI systems could verify user identity with over 90% accuracy.
The tech could then be used in many applications such as online banking and others.