Adversarial images with downscaling
Document type :
Communication dans un congrès avec actes
Title :
Adversarial images with downscaling
Author(s) :
Furon, Teddy [Auteur]
Creating and exploiting explicit links between multimedia fragments [LinkMedia]
Bonnet, Benoit [Auteur]
Creating and exploiting explicit links between multimedia fragments [LinkMedia]
Bas, Patrick [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Creating and exploiting explicit links between multimedia fragments [LinkMedia]
Bonnet, Benoit [Auteur]
Creating and exploiting explicit links between multimedia fragments [LinkMedia]
Bas, Patrick [Auteur]

Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Conference title :
ICIP 2022 - 29th IEEE International Conference on Image Processing
City :
Bordeaux
Country :
France
Start date of the conference :
2022-10-16
Publisher :
IEEE
HAL domain(s) :
Informatique [cs]/Traitement du signal et de l'image [eess.SP]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-03806425/document
- Open access
- Access the document
- https://hal.inria.fr/hal-03806425/document
- Open access
- Access the document
- https://hal.inria.fr/hal-03806425/document
- Open access
- Access the document
- document
- Open access
- Access the document
- Template.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- Template.pdf
- Open access
- Access the document