Steganalysis with cover-source mismatch and a small learning database - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

Steganalysis with cover-source mismatch and a small learning database

(1) , (2, 3) , (1)
1
2
3
Jérôme Pasquet
Marc Chaumont

Abstract

Many different hypotheses may be chosen for modeling a steganography/steganalysis problem. In this paper, we look closer into the case in which Eve, the steganalyst, has partial or erroneous knowledge of the cover distribution. More precisely we suppose that Eve knows the algorithms and the payload size that has been used by Alice, the steganographer, but she ignores the images distribution. In this source-cover mismatch scenario, we demonstrate that an Ensemble Classifier with Features Selection (EC-FS) allows the steganalyst to obtain the best state-of-the-art performances, while requiring 100 times smaller training database compared to the previous state-of-the art approach. Moreover, we propose the islet approach in order to increase the classification performances.
Fichier principal
Vignette du fichier
EUSIPCO2014-PASQUET_BRINGAY_CHAUMONT_EC-FS_cover_source_mismatch.pdf (249.37 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

lirmm-01234249 , version 1 (26-11-2015)

Identifiers

  • HAL Id : lirmm-01234249 , version 1

Cite

Jérôme Pasquet, Sandra Bringay, Marc Chaumont. Steganalysis with cover-source mismatch and a small learning database. EUSIPCO: European Signal Processing Conference, Sep 2014, Lisbon, Portugal. pp.2425-2429. ⟨lirmm-01234249⟩
195 View
205 Download

Share

Gmail Facebook Twitter LinkedIn More