Home / Current Issue / Paper 1718767
A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness
Subject area: Science,Engineering and Technology · Area of research: Image Steganalysis
DOI: https://doi.org/10.64388/IREV9I12-1718767
Abstract
This survey presents an overview of the development of image steganalysis from basic statistical models to the latest deep learning architectures. A total of 24 significant studies were analyzed, which are grouped into six important dimensions: embedding domain coverage, dataset diversity, low-payload sensitivity, adversarial robustness, pixel-level defense evaluation, computational efficiency. It also shows that the literature is fragmented, with no existing model that effectively covers the cases of heterogeneous dual-domain detection, realistic adversarial robustness on pixel level, and lightweight deployment. Three main gaps were identified: cover-source mismatch in the case of homogeneous training data, single domain architectural limitations, feature space adversarial evaluation that does not represent actual threat models; a unified taxonomy for future research is proposed. This survey provides a well-founded base for quantifying dataset heterogeneity from an information theoretic perspective, providing a principled ground for assessing generalisability in steganalysis systems.
Keywords
Adversarial Robustness, Dual-Domain Detection, Cover-Source Mismatch, Steganalysis.
How to cite this paper
@article{1718767,
author = {Shehu Asmau, Kirubakaran Prema, Muhammad L. Bilkisu},
title = {A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {12},
pages = {1372-1383},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1718767.pdf},
abstract = {This survey presents an overview of the development of image steganalysis from basic statistical models to the latest deep learning architectures. A total of 24 significant studies were analyzed, which are grouped into six important dimensions: embedding domain coverage, dataset diversity, low-payload sensitivity, adversarial robustness, pixel-level defense evaluation, computational efficiency. It also shows that the literature is fragmented, with no existing model that effectively covers the cases of heterogeneous dual-domain detection, realistic adversarial robustness on pixel level, and lightweight deployment. Three main gaps were identified: cover-source mismatch in the case of homogeneous training data, single domain architectural limitations, feature space adversarial evaluation that does not represent actual threat models; a unified taxonomy for future research is proposed. This survey provides a well-founded base for quantifying dataset heterogeneity from an information theoretic perspective, providing a principled ground for assessing generalisability in steganalysis systems.},
keywords = {Adversarial Robustness, Dual-Domain Detection, Cover-Source Mismatch, Steganalysis.},
month = {June},
doi = {https://doi.org/10.64388/IREV9I12-1718767}
}