A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness

• Author(s): Shehu Asmau; Kirubakaran Prema; Muhammad L. Bilkisu
• Paper ID: 1718767
• Page: 1372-1383
• Published Date: 15-06-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 12 June-2026
• 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.

Citations

IRE Journals:
Shehu Asmau, Kirubakaran Prema, Muhammad L. Bilkisu "A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness" Iconic Research And Engineering Journals Volume 9 Issue 12 2026 Page 1372-1383 https://doi.org/10.64388/IREV9I12-1718767

IEEE:
Shehu Asmau, Kirubakaran Prema, Muhammad L. Bilkisu "A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness" Iconic Research And Engineering Journals, vol. 9, no. 12, Jun. 2026, doi: https://doi.org/10.64388/IREV9I12-1718767

APA:
Shehu Asmau, Kirubakaran Prema, Muhammad L. Bilkisu (2026). A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness. Iconic Research And Engineering Journals, 9(12). doi: https://doi.org/10.64388/IREV9I12-1718767

MLA:
Shehu Asmau, Kirubakaran Prema, Muhammad L. Bilkisu "A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness" Iconic Research And Engineering Journals, vol. 9, no. 12, Jun. 2026. Crossref, https://doi.org/10.64388/IREV9I12-1718767

BibTeX

@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}
}