FoggySight: A Scheme for Facial Lookup Privacy
This work tackles the problem of facial lookup privacy for social media users, offering a novel approach to protect individuals from unauthorized face recognition.
This paper addresses the privacy risks associated with face recognition systems by proposing FoggySight, a scheme that modifies facial photos before they are uploaded to social media. FoggySight uses adversarial machine learning to generate decoy photos, enabling protection against facial recognition services even with unknown internal workings.
Advances in deep learning algorithms have enabled better-than-human performance on face recognition tasks. In parallel, private companies have been scraping social media and other public websites that tie photos to identities and have built up large databases of labeled face images. Searches in these databases are now being offered as a service to law enforcement and others and carry a multitude of privacy risks for social media users. In this work, we tackle the problem of providing privacy from such face recognition systems. We propose and evaluate FoggySight, a solution that applies lessons learned from the adversarial examples literature to modify facial photos in a privacy-preserving manner before they are uploaded to social media. FoggySight's core feature is a community protection strategy where users acting as protectors of privacy for others upload decoy photos generated by adversarial machine learning algorithms. We explore different settings for this scheme and find that it does enable protection of facial privacy -- including against a facial recognition service with unknown internals.