What if Adversarial Samples were Digital Images? - Archive ouverte HAL Access content directly
Conference Papers Year :

What if Adversarial Samples were Digital Images?


Although adversarial sampling is a trendy topic in computer vision , very few works consider the integral constraint: The result of the attack is a digital image whose pixel values are integers. This is not an issue at first sight since applying a rounding after forging an adversarial sample trivially does the job. Yet, this paper shows theoretically and experimentally that this operation has a big impact. The adversarial perturbations are fragile signals whose quantization destroys its ability to delude an image classifier. This paper presents a new quantization mechanism which preserves the adversariality of the perturbation. Its application outcomes to a new look at the lessons learnt in adversarial sampling.
Fichier principal
Vignette du fichier
main_finalWOcopy.pdf (3.01 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02553006 , version 1 (06-05-2020)
hal-02553006 , version 2 (13-05-2020)



Benoît Bonnet, Teddy Furon, Patrick Bas. What if Adversarial Samples were Digital Images?. IH&MMSEC 2020 - 8th ACM Workshop on Information Hiding and Multimedia Security, Jun 2020, Denver, France. pp.1-11, ⟨10.1145/3369412.3395062⟩. ⟨hal-02553006v2⟩
244 View
186 Download



Gmail Facebook Twitter LinkedIn More