Security researchers have demonstrated a system by which they can use publicly available photos of an individual to trick facial recognition technology and achieve successful authentication. Their approach tricked all but 1D with a success rate of 55 percent to 85 percent. The team recommends using sensors to detect subtle changes in skin tone texturing and light patterns that might suggest a spoofing attack is underway. These findings mean facial recognition-based authentication technology needs to change: “Our work outlines several important lessons for both the present and the future state of security”””
Source: https://www.bleepingcomputer.com/news/security/how-to-trick-facial-recognition-tech-with-a-facebook-photo/

