Skip to Main content Skip to Navigation
Conference papers

The Cover Source Mismatch Problem in Deep-Learning Steganalysis

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.
Complete list of metadata

https://hal-utt.archives-ouvertes.fr/hal-03694662
Contributor : Rémi Cogranne Connect in order to contact the contributor
Submitted on : Monday, June 13, 2022 - 9:11:12 PM
Last modification on : Wednesday, September 7, 2022 - 8:14:05 AM

File

Giboulot_EUSIPCO_2022.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03694662, version 1

Citation

Quentin Giboulot, Patrick Bas, Rémi Cogranne, Dirk Borghys. The Cover Source Mismatch Problem in Deep-Learning Steganalysis. European Signal Processing Conference, Aug 2022, Belgrade, Serbia. ⟨hal-03694662⟩

Share

Metrics

Record views

43

Files downloads

42