Adversarial images with downscaling - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Adversarial images with downscaling

Résumé

Most works on adversarial attacks consider small images whose size already fits the model. This paper explores attacking large images on classifiers with different input sizes. Downscaling is a necessary first step to adapt the size of the image to the model that might reform the adversarial signal. This paper studies the possibility of forging adversarial images through different interpolation methods, the distortion of their adversarial signal, and the transferability over other downscaling methods. This paper finally explores attacking an ensemble model which gathers different resizing interpolations to increase the transferability of the attack against a set downscaling kernels.
Fichier principal
Vignette du fichier
Template.pdf (435.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03806425 , version 1 (07-10-2022)

Identifiants

  • HAL Id : hal-03806425 , version 1

Citer

Teddy Furon, Benoit Bonnet, Patrick Bas. Adversarial images with downscaling. ICIP 2022 - 29th IEEE International Conference on Image Processing, Oct 2022, Bordeaux, France. pp.1-5. ⟨hal-03806425⟩
39 Consultations
79 Téléchargements

Partager

Gmail Facebook X LinkedIn More