L 1-norm double backpropagation adversarial defense - Université Clermont Auvergne Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

L 1-norm double backpropagation adversarial defense

Résumé

Adversarial examples are a challenging open problem for deep neural networks. We propose in this paper to add a penalization term that forces the decision function to be at in some regions of the input space, such that it becomes, at least locally, less sensitive to attacks. Our proposition is theoretically motivated and shows on a rst set of carefully conducted experiments that it behaves as expected when used alone, and seems promising when coupled with adversarial training.
Fichier principal
Vignette du fichier
main.pdf (473.75 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02049020 , version 1 (05-03-2019)

Identifiants

Citer

Ismaïla Seck, Gaëlle Loosli, Stephane Canu. L 1-norm double backpropagation adversarial defense. ESANN - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2019, Bruges, France. ⟨hal-02049020⟩
140 Consultations
99 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More