The Cover Source Mismatch Problem in ...
Document type :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Title :
The Cover Source Mismatch Problem in Deep-Learning Steganalysis
Author(s) :
Giboulot, Quentin [Auteur]
Laboratoire Modélisation et Sûreté des Systèmes [LM2S]
Bas, Patrick [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Cogranne, Rémi [Auteur]
Laboratoire Modélisation et Sûreté des Systèmes [LM2S]
Dirk, Borghys [Auteur]
Ecole Royale Militaire / Koninklijke Militaire School [ERM KMS]
Laboratoire Modélisation et Sûreté des Systèmes [LM2S]
Bas, Patrick [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Cogranne, Rémi [Auteur]
Laboratoire Modélisation et Sûreté des Systèmes [LM2S]
Dirk, Borghys [Auteur]
Ecole Royale Militaire / Koninklijke Militaire School [ERM KMS]
Conference title :
2022 30th European Signal Processing Conference (EUSIPCO)
City :
Belgrade
Start date of the conference :
2022-08-29
Publisher :
IEEE
Publication date :
2022
English keyword(s) :
Training
Deep learning
Sensitivity
ISO
Pipelines
Signal processing
Deep learning
Sensitivity
ISO
Pipelines
Signal processing
HAL domain(s) :
Informatique [cs]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :