Universal Adversarial Perturbations: Efficiency on a small image dataset - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Universal Adversarial Perturbations: Efficiency on a small image dataset

Résumé

Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly changing an input image. A paper has shown the existence of Universal Adversarial Perturbations which when added to any image will fool the neural network with a very high probability. In this paper we will try to reproduce the experience of the Universal Adversarial Perturbations paper, but on a smaller neural network architecture and training set, in order to be able to study the efficiency of the computed perturbation.
Fichier principal
Vignette du fichier
paper.pdf (3.34 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03806871 , version 1 (10-10-2022)

Identifiants

Citer

Waris Radji. Universal Adversarial Perturbations: Efficiency on a small image dataset. 2022. ⟨hal-03806871⟩
25 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More