Size-Independent Reliable CNN for RJCA Steganalysis

Butora, Jan; Bas, Patrick

Type de document :

Article dans une revue scientifique: Article original

DOI :

10.1109/TIFS.2024.3379849

Titre :

Size-Independent Reliable CNN for RJCA Steganalysis

Auteur(s) :

Butora, Jan [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Bas, Patrick [Auteur]

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

Titre de la revue :

IEEE Transactions on Information Forensics and Security

Pagination :

2683-2695

Éditeur :

Institute of Electrical and Electronics Engineers

Date de publication :

2024-03-20

ISSN :

1556-6013

Mot(s)-clé(s) en anglais :

Steganalysis
false positive control
JPEG
arbitrary size

Discipline(s) HAL :

Informatique [cs]/Cryptographie et sécurité [cs.CR]
Informatique [cs]/Multimédia [cs.MM]

Résumé en anglais : [en]

Detection of image steganography is principally implemented with supervised machine learning detectors. There are two main drawbacks to this approach: the detectors are overly specific to a given image source, and the ...
Lire la suite >Detection of image steganography is principally implemented with supervised machine learning detectors. There are two main drawbacks to this approach: the detectors are overly specific to a given image source, and the performance guarantees are only empirical. In this work, we further study a previously proposed deep learning detector that exploits natural image structure imposed by JPEG compression with high quality. We show in a controlled environment that for a fixed JPEG compressor, the soft outputs of a deep learning classifier-the logits-follow a Gaussian distribution. We prove a scaling law stating that the variance of this distribution scales linearly with the image size. By disabling padding in the convolutional neural network, we demonstrate that the mean of the logit distribution does not change, allowing us to directly analyze images of different sizes. Focusing on the logits, we show that we can prescribe a threshold with a theoretical false positive rate for a wide range of image sizes, which is then closely satisfied on real cover images, even for small probabilities such as 10^{−4}. Moreover, the detection power on steganographic images still generalizes to non-adaptive and content-adaptive steganography.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Fichiers

document
Accès libre
Accéder au document

scaling_03.pdf
Accès libre
Accéder au document

Size-Independent Reliable CNN for RJCA ... BibTeX CSV Excel RIS

Fichiers

Size-Independent Reliable CNN for RJCA ...

BibTeX

CSV

Excel

RIS