Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
Published in
USENIX Security Symposium(2020)External Links:
TL
TL;DR
Fawkes is a system that helps individuals inoculate their images against unauthorized facial recognition models by helping users add imperceptible pixel-level changes to their own photos before releasing them, and is robust against a variety of countermeasures that try to detect or disrupt image cloaks.