Researchers from McAfee showed how they were able to trick a facial-recognition system into misclassifying one individual as an entirely different person. The researchers built a machine-learning model and fed it training data: a set of 1,500 photos of two separate individuals. The model then continuously created and tested fake images of the two individuals by blending the facial features of both subjects. The passport-verification system attack scenario is theoretically possible to carry out, Steve Povolny says.”]
Source: https://www.darkreading.com/attacks-breaches/researchers-trick-facial-recognition-systems