Smooth Adversarial Examples - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Smooth Adversarial Examples

(1) , (1) , (1) , (1)
1

Abstract

This paper investigates the visual quality of the adver-sarial examples. Recent papers propose to smooth the perturbations to get rid of high frequency artefacts. In this work, smoothing has a different meaning as it perceptually shapes the perturbation according to the visual content of the image to be attacked. The perturbation becomes locally smooth on the flat areas of the input image, but it may be noisy on its textured areas and sharp across its edges. This operation relies on Laplacian smoothing, well-known in graph signal processing, which we integrate in the attack pipeline. We benchmark several attacks with and without smoothing under a white-box scenario and evaluate their transferability. Despite the additional constraint of smoothness, our attack has the same probability of success at lower distortion.
Fichier principal
Vignette du fichier
1903.11862.pdf (5.34 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02370202 , version 1 (19-11-2019)

Identifiers

Cite

Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg. Smooth Adversarial Examples. 2019. ⟨hal-02370202⟩
67 View
130 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More