PrivacyGAN: robust generative image privacy

no code implementations • 19 Oct 2023 • Mariia Zameshina, Marlene Careil, Olivier Teytaud, Laurent Najman

Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images resembling the original only in several characteristics, such as gender, ethnicity, or facial expression. In this study, we introduce a novel approach, PrivacyGAN, that uses the power of image generation techniques, such as VQGAN and StyleGAN, to safeguard privacy while maintaining image usability, particularly for social media applications.

Data Poisoning Image Generation