收藏切换
A Generative Image Steganography Method Based on Dual Diffusion Models for Unknown Source-Target Domains
收藏切换
Yunyun Dong1, 2, Jinhong Zhang1, Fanxiao Li1, Bo Zhu2, Wei Zhou3, *
Journal of Computer Research and Development | 2026, 63(7) : 1831 - 1841
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(7): 1831-1841
• Artificial Intelligence •
A Generative Image Steganography Method Based on Dual Diffusion Models for Unknown Source-Target Domains
Full
Yunyun Dong1, 2, Jinhong Zhang1, Fanxiao Li1, Bo Zhu2, Wei Zhou3, *
Affiliations
  • 1School of Information Science and Engineering, Yunnan University, Kunming 650504
  • 2School of Software and AI, Yunnan University, Kunming 650504
  • 3School of Engineering, Yunnan University, Kunming 650500
  • born in 1989. PhD, lecturer. Member of CCF. Her main research interests include image steganography and large model security

    born in 1999. PhD candidate. Student member of CCF. His main research interests include AI model security and multimedia data privacy protection

    born in 1998. PhD candidate. Student member of CCF and IEEE. His main research interests include misinformation detection and multi modal large language models

    born in 2001.Master candidate. His main research interests include privacy protection and image steganography

    born in 1974. Professor, PhD supervisor. Senior member of CCF. His main research interests include cyberspace security, distributed cloud computing, intelligent information processing, and interdisciplinary research

About Author:

born in 1989. PhD, lecturer. Member of CCF. Her main research interests include image steganography and large model security

born in 1999. PhD candidate. Student member of CCF. His main research interests include AI model security and multimedia data privacy protection

born in 1998. PhD candidate. Student member of CCF and IEEE. His main research interests include misinformation detection and multi modal large language models

born in 2001.Master candidate. His main research interests include privacy protection and image steganography

born in 1974. Professor, PhD supervisor. Senior member of CCF. His main research interests include cyberspace security, distributed cloud computing, intelligent information processing, and interdisciplinary research

Published: 2026-07-01 doi: 10.7544/issn1000-1239.202550348
Outline
收藏切换

The rapid expansion of social networks has made data transmission over public channels ubiquitous, raising serious security and privacy concerns. Although encryption can guarantee confidentiality, its distinctive format may arouse suspicion. Steganography offers a covert alternative by hiding secret data within ordinary media, such as images, text, or audio, thereby reducing the risk of detection. Traditional pixel-editing steganographic methods are vulnerable to steganalysis or compression artifacts, while existing generative approaches often depend on tailored prompts or specific data sources, limiting their generalization and flexibility. To address these challenges, we propose a source-agnostic, target-domain image steganography framework based on a dual diffusion model. First, this method employs a latent diffusion model (LDM) to invert and optimize arbitrary secret images, obtaining high-fidelity latent representations. To eliminate residual structural cues from the LDM inversion that could compromise subsequent hiding and extraction, this method introduces a Gaussian structural reordering alignment module which encrypts the secret’s latent representation via pseudo-random orthogonal perturbation and spatial shuffling, preserving its norm while enforcing a Gaussian-like distribution that aligns with downstream inputs and enhances security. Finally, we use a denoising diffusion implicit models (DDIM) sampler to denoise and decode the encrypted latent vectors, producing stego images that faithfully reflect the target domain’s appearance while carrying the hidden content. Experiments on four public datasets demonstrate that our method requires no source-specific training, achieves strong cross-domain generalization, and significantly outperforms competing techniques in extraction accuracy, imperceptibility, and resistance to steganalysis.

image steganography  /  image generation  /  diffusion model  /  strong generalizability  /  distribution shift
董云云, 张锦弘, 李钒效, 朱波, 周维. 基于双扩散模型的未知源-目标域生成式图像隐写方法. 计算机研究与发展, 2026 , 63 (7) : 1831 -1841 . DOI: 10.7544/issn1000-1239.202550348
Yunyun Dong, Jinhong Zhang, Fanxiao Li, Bo Zhu, Wei Zhou. A Generative Image Steganography Method Based on Dual Diffusion Models for Unknown Source-Target Domains[J]. Journal of Computer Research and Development, 2026 , 63 (7) : 1831 -1841 . DOI: 10.7544/issn1000-1239.202550348
Year 2026 volume 63 Issue 7
57
25
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550348
  • Receive Date:2025-05-26
  • Online Date:2026-11-17
  • Published:2026-07-01
Article Data
Affiliations
History
  • Received:2025-05-26
  • Revised:2026-03-25
  • Accepted:2026-04-07
Affiliations
    1School of Information Science and Engineering, Yunnan University, Kunming 650504
    2School of Software and AI, Yunnan University, Kunming 650504
    3School of Engineering, Yunnan University, Kunming 650500
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550348
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT