BS-ADV: a secure black-box image steganography framework enhanced by adversarial sample attack
Advanced Information and Communication · 29.06.2026 · 1-26
DOI: 10.55092/aic20260009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Information and Communication, online erschienen am 29.06.2026. Verfasst von Shichen Yang und 5 weiteren Autor:innen.
Abstract (Originalsprache)
: Mainstream image steganography approaches struggle to evade increasingly accurate steganalyzers, while many security-enhancement techniques require white-box access to the steganographic encoder, hindering deployment in black-box settings. We address this gap with a framework that achieves strong security and high image quality without access to encoder internals. Our method Black-box Steganography via Transferable Adversarial Attack (BS-ADV) adds small, transferable adversarial perturbations to stego images using gradients from a chosen steganalysis model, yet remains independent of the steganographic encoder. Building on this idea, we instantiate two variants: FGSM-adv, which applies a single-step
Zitieren
APA
Yang, S., Xu, H., Jia, X., Ye, G., Yuan, C., & Zhou, H. (2026). BS-ADV: a secure black-box image steganography framework enhanced by adversarial sample attack. Advanced Information and Communication, 1-26. https://doi.org/10.55092/aic20260009
Vancouver
Yang S, Xu H, Jia X, Ye G, Yuan C, Zhou H. BS-ADV: a secure black-box image steganography framework enhanced by adversarial sample attack. Advanced Information and Communication. 2026:1-26. doi:10.55092/aic20260009
BibTeX
@article{Yang2026,
author = {Yang, Shichen and Xu, Haiyu and Jia, Xingxing and Ye, Guodong and Yuan, Chengsheng and Zhou, Huiyu},
title = {BS-ADV: a secure black-box image steganography framework enhanced by adversarial sample attack},
journal = {Advanced Information and Communication},
year = {2026},
pages = {1--26},
doi = {10.55092/aic20260009}
}
EUVIMED