Walking on the Edge: Fast, Low-Distortion Adversarial Examples - Archive ouverte HAL
Journal Articles IEEE Transactions on Information Forensics and Security Year : 2020

Walking on the Edge: Fast, Low-Distortion Adversarial Examples

Abstract

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks in our everyday lives. When white-box attacks are almost always successful, it is typically only the distortion of the perturbations that matters in their evaluation. In this work, we argue that speed is important as well, especially when considering that fast attacks are required by adversarial training. Given more time, iterative methods can always find better solutions. We investigate this speed-distortion trade-off in some depth and introduce a new attack called boundary projection (BP) that improves upon existing methods by a large margin. Our key idea is that the classification boundary is a manifold in the image space: we therefore quickly reach the boundary and then optimize distortion on this manifold.
Fichier principal
Vignette du fichier
bp.pdf (4.27 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02931493 , version 1 (08-12-2020)

Identifiers

Cite

Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg. Walking on the Edge: Fast, Low-Distortion Adversarial Examples. IEEE Transactions on Information Forensics and Security, 2020, 16, pp.701 - 713. ⟨10.1109/TIFS.2020.3021899⟩. ⟨hal-02931493⟩
158 View
137 Download

Altmetric

Share

More