From Pixel Modification to Generative Synthesis: A Survey of Deep Learning for Image Data Hiding
Journal of Imaging · 04.09.2026 · 12 (9) · 417
DOI: 10.3390/jimaging12090417 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Journal of Imaging, online erschienen am 04.09.2026. Verfasst von Matúš Janok und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Informatics, Slovak Academy of Sciences, 845 07 Bratislava, Slovakia. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 188 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Recovery and Resilience Plan for Slovakia, Slovak Scientific Grant Agency VEGA, Slovak Research and Development Agency.
Abstract (Originalsprache)
This survey presents a structured review of deep learning-based techniques for image data hiding, proposing a three-paradigm taxonomy organized by the method’s operational relationship to the carrier image. We classify existing methods into modification-based, synthesis-based, and logic-based approaches. In the modification-based tier, we trace the architectural progression from foundational Convolutional Neural Networks and Generative Adversarial Networks to high-capacity Invertible Neural Networks and Transformers, analyzing their distinct trade-offs between embedding capacity, imperceptibility, and robustness. In the synthesis-based tier, we examine how Diffusion Probabilistic Models and generative adversarial frameworks reframe data hiding as a carrier generation problem rather than a pixel editing task. This paradigm encompasses both generative steganography (where carriers are synthesized from scratch) and proactive watermarking (where provenance is embedded during AI content generation). In the logic-based tier, we review zero-watermarking and coverless steganography, where ownership is established through feature extraction and semantic mapping without modifying any image, a critical property for sensitive domains such as medical imaging. Finally, we identify four persistent infrastructure gaps: benchmarking fragmentation, narrow robustness evaluation, domain generalization failures, and computational infeasibility that prevent real-world deployment despite architectural progress, and we propose concrete research directions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Informatics, Slovak Academy of Sciences, 845 07 Bratislava, Slovakia.
ORCID-Profile: Matúš Janok, Radoslav Forgáč, Ladislav Hluchý
Förderung
- Recovery and Resilience Plan for Slovakia
- Slovak Scientific Grant Agency VEGA
- Slovak Research and Development Agency
Zitieren
APA
Janok, M., Forgáč, R., & Hluchý, L. (2026). From Pixel Modification to Generative Synthesis: A Survey of Deep Learning for Image Data Hiding. Journal of Imaging, 12(9), 417. https://doi.org/10.3390/jimaging12090417
Vancouver
Janok M, Forgáč R, Hluchý L. From Pixel Modification to Generative Synthesis: A Survey of Deep Learning for Image Data Hiding. Journal of Imaging. 2026;12(9):417. doi:10.3390/jimaging12090417
BibTeX
@article{Janok2026,
author = {Janok, Matúš and Forgáč, Radoslav and Hluchý, Ladislav},
title = {From Pixel Modification to Generative Synthesis: A Survey of Deep Learning for Image Data Hiding},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {9},
pages = {417},
doi = {10.3390/jimaging12090417}
}
EUVIMED