Smooth Adversarial Examples

Hanwei Zhang 1 Yannis Avrithis 1 Teddy Furon 1 Laurent Amsaleg 1
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [41 references]  Display  Hide  Download

https://hal.inria.fr/hal-02370202
Contributor : Yannis Avrithis <>
Submitted on : Tuesday, November 19, 2019 - 12:48:55 PM
Last modification on : Thursday, November 21, 2019 - 1:21:05 AM

File

1903.11862.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02370202, version 1
  • ARXIV : 1903.11862

Citation

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

Share

Metrics

Record views

9

Files downloads

47