%0 Journal Article %T Effects and Solutions of Cover-Source Mismatch in Image Steganalysis %+ Laboratoire Modélisation et Sûreté des Systèmes (LM2S) %+ Ecole Royale Militaire / Koninklijke Militaire School (ERM KMS) %+ Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL) %+ Centre National de la Recherche Scientifique (CNRS) %A Giboulot, Quentin %A Cogranne, Rémi %A Borghys, Dirk %A Bas, Patrick %< avec comité de lecture %@ 0923-5965 %J Signal Processing: Image Communication %I Elsevier %S 86 %8 2020-08 %D 2020 %R 10.1016/j.image.2020.115888 %K Steganography %K Steganalysis %K Cover-Source Mismatch %K Image processing %K Image Heterogeneity %Z Computer Science [cs]/Cryptography and Security [cs.CR] %Z Engineering Sciences [physics]/Signal and Image processing %Z Statistics [stat]/Applications [stat.AP]Journal articles %X The Cover-Source Mismatch (CSM) has been long recognized as a major problem in modern steganography and steganalysis. Indeed, while a vast majority of works in steganography and steganalysis had been tailored to a specific reference database, namely BOSSbase, recent works show that, because of CSM, the results may greatly differ when changing this dataset. Although the CSM has already been the subject of several publications, these prior works investigated only a few elements in a limited setup. The goal of the current paper is to study the effects of the CSM in a more comprehensive manner and then to examine and compare different strategies for mitigating it. It first defines two different parameters, the source difficulty and the source inconsistency, which are involved in the CSM. Then, using different steganographic schemes and feature sets, it aims at providing a systematic study regarding the various factors that can give birth to CSM for image steganalysis. Finally, two practical ways to mitigate the CSM, using training techniques promoting either diversity of different sources or the specificity of one targeted source which is beforehand identified by training a multi-class classifier, are presented and their performances are compared for different training set sizes. %G English %2 https://utt.hal.science/hal-02631559/document %2 https://utt.hal.science/hal-02631559/file/ImageCommunication_Final.pdf %L hal-02631559 %U https://utt.hal.science/hal-02631559 %~ CNRS %~ UNIV-TROYES %~ CRISTAL %~ CRISTAL-SIGMA %~ UNIV-LILLE %~ UTT %~ TEST-HALCNRS %~ ANR %~ UTT-LIST3N %~ UTT-FULL-TEXT %~ LM2S-UTT