"Researchers Trick Facial Recognition Systems"

McAfee researchers were able to trick a facial recognition system into misclassifying one person as another person using Generative Adversarial Networks (GANs). GANs are neural networks that can create data similar to the data it is fed. In the study, GANs produced fully-synthetic real-looking images of human faces from input containing a set of real pictures of human faces. Advancements in Artificial Intelligence (AI) and Machine Learning (ML) continue to increase the level of skill at which neural networks generate photo-realistic images of human faces that can deceive facial recognition systems. This article continues to discuss how McAfee researchers tricked facial recognition systems into misclassifying an individual as a completely different person, the researchers' theoretical passport-verification system attack, and how vendors can improve the security of facial recognition technology. 

Dark Reading reports "Researchers Trick Facial-Recognition Systems"