The Cover Source Mismatch Problem in Deep-Learning Steganalysis

Giboulot Quentin, Bas Patrick, Cogranne Rémi, Borghys Dirk

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

Abstract

This paper studies the problem of Cover Source Mismatch (CSM) in steganalysis, i.e. the impact of a testing set which does not originate from the same source than the training set. In this study, the trained steganalyzer uses state of the art deep-learning architecture prone to better generalization than feature-based steganalysis. Different sources such as the sensor model, the ISO sensitivity, the processing pipeline and the content, are investigated. Our conclusions are that, on one hand, deep learning steganalysis is still very sensitive to the CSM, on the other hand, the holistic strategy leverages the good generalization properties of deep learning to reduce the CSM with a relatively small number of training samples.

OriginalspracheEnglisch
Titel30th European Signal Processing Conference, EUSIPCO 2022 - Proceedings
Herausgeber (Verlag)European Signal Processing Conference, EUSIPCO
Seiten1032-1036
Seitenumfang5
ISBN (elektronisch)9789082797091
PublikationsstatusVeröffentlicht - 2022
Veranstaltung30th European Signal Processing Conference, EUSIPCO 2022 - Belgrade, Serbien
Dauer: 29 Aug. 20222 Sept. 2022

Publikationsreihe

NameEuropean Signal Processing Conference
Band2022-August
ISSN (Print)2219-5491

Konferenz

Konferenz30th European Signal Processing Conference, EUSIPCO 2022
Land/GebietSerbien
OrtBelgrade
Zeitraum29/08/222/09/22

Fingerprint

Untersuchen Sie die Forschungsthemen von „The Cover Source Mismatch Problem in Deep-Learning Steganalysis“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren