Forensics Through Stega Glasses: the Case of Adversarial Images

Bonnet, Benoît; Furon, Teddy; Bas, Patrick

Document type :

Communication dans un congrès avec actes

Title :

Forensics Through Stega Glasses: the Case of Adversarial Images

Author(s) :

Bonnet, Benoît [Auteur]
Creating and exploiting explicit links between multimedia fragments [LinkMedia]
Furon, Teddy [Auteur]
Creating and exploiting explicit links between multimedia fragments [LinkMedia]
Bas, Patrick [Auteur]

Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]

Conference title :

ICPR-MMForWILD 2020 - Workshop MultiMedia FORensics in the WILD

City :

Milan

Country :

Italie

Start date of the conference :

2021-01-10

Journal title :

Pattern Recognition: ICPR International Workshops and Challenges

Publisher :

Springer International Publishing

Publication date :

2021-01

English keyword(s) :

Adversarial Examples
Steganography
Image Forensics

HAL domain(s) :

Sciences de l'ingénieur [physics]/Traitement du signal et de l'image [eess.SP]

English abstract : [en]

This paper explores the connection between forensics, counterforensics, steganography and adversarial images. On the one hand, forensicsbased and steganalysis-based detectors help in detecting adversarial perturbations. ...
Show more >This paper explores the connection between forensics, counterforensics, steganography and adversarial images. On the one hand, forensicsbased and steganalysis-based detectors help in detecting adversarial perturbations. On the other hand, steganography can be used as a counterforensics strategy and helps in forging adversarial perturbations that are not only invisible to the human eye but also less statistically detectable. This work explains how to use these information hiding tools for attacking or defending computer vision image classification. We play this cat and mouse game using both recent deep-learning content-based classifiers, forensics detectors derived from steganalysis, and steganographic distortions dedicated to color quantized images. It turns out that crafting adversarial perturbations relying on steganographic perturbations is an effective counter-forensics strategy.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Sécurité de l'Intelligence Artificielle pour des Applications Défense

Collections :