Generating Private Data Surrogates for Vision Related Tasks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Generating Private Data Surrogates for Vision Related Tasks

Résumé

With the widespread application of deep networks in industry, membership inference attacks, i.e. the ability to discern training data from a model, become more and more problematic for data privacy. Recent work suggests that generative networks may be robust against membership attacks. In this work, we build on this observation, offering a general-purpose solution to the membership privacy problem. As the primary contribution, we demonstrate how to construct surrogate datasets, using images from GAN generators, labelled with a classifier trained on the private dataset. Next, we show this surrogate data can further be used for a variety of downstream tasks (here classification and regression), while being resistant to membership attacks. We study a variety of different GANs proposed in the literature, concluding that higher quality GANs result in better surrogate data with respect to the task at hand.
Fichier principal
Vignette du fichier
Generated_Private_Interfaces_ICML_Workshop.pdf (13.55 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02367948 , version 1 (18-11-2019)
hal-02367948 , version 2 (21-11-2019)

Identifiants

  • HAL Id : hal-02367948 , version 2

Citer

Ryan Webster, Julien Rabin, Loïc Simon, Frédéric Jurie. Generating Private Data Surrogates for Vision Related Tasks. ICPR 2020, International Association of Pattern Recognition, IAPR, Jan 2021, Milan, Italy. ⟨hal-02367948v2⟩
116 Consultations
54 Téléchargements

Partager

Gmail Facebook X LinkedIn More