PrivacyGAN: robust generative image privacy - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

PrivacyGAN: robust generative image privacy

Mariia Zameshina
  • Fonction : Auteur
  • PersonId : 1294681
Olivier Teytaud

Résumé

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. Drawing inspiration from Fawkes, our method entails shifting the original image within the embedding space towards a decoy image. We evaluate our approach using privacy metrics on traditional and novel facial image datasets. Additionally, we propose new criteria for evaluating the robustness of privacy-protection methods against unknown image recognition techniques, and we demonstrate that our approach is effective even in unknown embedding transfer scenarios. We also provide a human evaluation that further proves that the modified image preserves its utility as it remains recognisable as an image of the same person by friends and family.
Fichier principal
Vignette du fichier
main.pdf (6.14 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04248792 , version 1 (18-10-2023)

Licence

Paternité - Partage selon les Conditions Initiales

Identifiants

Citer

Mariia Zameshina, Marlene Careil, Olivier Teytaud, Laurent Najman. PrivacyGAN: robust generative image privacy. 2023. ⟨hal-04248792⟩
52 Consultations
16 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More