Description
Fawkes is an image cloaking system that helps individuals inoculate their images against unauthorized facial recognition models. Fawkes achieves this by helping users add imperceptible pixel-level changes ("cloaks") to their own photos before releasing them. When used to train facial recognition models, these "cloaked" images produce functional models that consistently cause normal images of the user to be misidentified.
Papers Using This Method
PrivacyGAN: robust generative image privacy2023-10-19Data Poisoning Won't Save You From Facial Recognition2021-06-28Data Poisoning Won’t Save You From Facial Recognition2021-06-18Oriole: Thwarting Privacy against Trustworthy Deep Learning Models2021-02-23Fawkes: Protecting Privacy against Unauthorized Deep Learning Models2020-02-19