%0 Conference Proceedings
%T Improving Blind Steganalysis in Spatial Domain Using a Criterion to Choose the Appropriate Steganalyzer Between CNN and SRM+EC
%+ Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies (UMR 6174) (FEMTO-ST)
%A Couchot, Jean-François
%A Couturier, Raphaël
%A Salomon, Michel
%Z Part 6: Applied Cryptography and Voting Schemes
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 32th IFIP International Conference on ICT Systems Security and Privacy Protection (SEC)
%C Rome, Italy
%Y Sabrina De Capitani di Vimercati
%Y Fabio Martinelli
%I Springer International Publishing
%3 ICT Systems Security and Privacy Protection
%V AICT-502
%P 327-340
%8 2017-05-29
%D 2017
%R 10.1007/978-3-319-58469-0_22
%K Steganalysis
%K Spatial domain
%K CNN
%K SRM+EC
%Z Computer Science [cs]Conference papers
%X Conventional state-of-the-art image steganalysis approaches usually consist of a classifier trained with features provided by rich image models. As both features extraction and classification steps are perfectly embodied in the deep learning architecture called Convolutional Neural Network (CNN), different studies have tried to design a CNN-based steganalyzer. This work proposes a criterion to choose either the CNN designed by Xu et al. or the combination Spatial Rich Models (SRM) and Ensemble Classifier (EC) for an input image. Our approach is studied with three steganographic spatial domain algorithms: S-UNIWARD, MiPOD, and HILL, and exhibits detection capabilities better than each method alone. As SRM+EC and the CNN are only trained with MiPOD the proposed method can be seen as an approach for blind steganalysis.
%G English
%Z TC 11
%2 https://inria.hal.science/hal-01649001/document
%2 https://inria.hal.science/hal-01649001/file/449885_1_En_22_Chapter.pdf
%L hal-01649001
%U https://inria.hal.science/hal-01649001
%~ CNRS
%~ UNIV-FCOMTE
%~ UNIV-BM
%~ ENSMM
%~ FEMTO-ST
%~ UNIV-BM-THESE
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC11
%~ IFIP-SEC
%~ IFIP-AICT-502