MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models

Zihao Xu, Dawei Xu, Zihan Li, Chuan Zhang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69832-69848, 2025.

Abstract

Generative image steganography (GIS) is an emerging technique that conceals secret messages in the generation of images. Compared to GAN-based or flow-based GIS schemes, diffusion model-based solutions can provide high-quality and more diverse images, thus receiving considerable attention recently. However, previous GIS schemes still face challenges in terms of extraction accuracy, controllability, and practicality. To address the above issues, this paper proposes a practical message-driven GIS framework based on diffusion models, called MDDM. Specifically, by utilizing the Cardan grille, we encode messages into Gaussian noise, which serves as the initial input for image generation, enabling users to generate diverse images via controllable prompts without additional training. During the information extraction process, receivers only need to use the pre-shared Cardan grille to perform diffusion inversion and recover the messages without requiring the image generation seeds or prompts. Experimental results demonstrate that MDDM offers notable advantages in terms of accuracy, controllability, practicality, and security. With flexible strategies, MDDM can achieve accuracy close to 100% under appropriate settings. Additionally, MDDM demonstrates certain robustness and potential for application in watermarking tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-xu25ah, title = {{MDDM}: Practical Message-Driven Generative Image Steganography Based on Diffusion Models}, author = {Xu, Zihao and Xu, Dawei and Li, Zihan and Zhang, Chuan}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {69832--69848}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/xu25ah/xu25ah.pdf}, url = {https://proceedings.mlr.press/v267/xu25ah.html}, abstract = {Generative image steganography (GIS) is an emerging technique that conceals secret messages in the generation of images. Compared to GAN-based or flow-based GIS schemes, diffusion model-based solutions can provide high-quality and more diverse images, thus receiving considerable attention recently. However, previous GIS schemes still face challenges in terms of extraction accuracy, controllability, and practicality. To address the above issues, this paper proposes a practical message-driven GIS framework based on diffusion models, called MDDM. Specifically, by utilizing the Cardan grille, we encode messages into Gaussian noise, which serves as the initial input for image generation, enabling users to generate diverse images via controllable prompts without additional training. During the information extraction process, receivers only need to use the pre-shared Cardan grille to perform diffusion inversion and recover the messages without requiring the image generation seeds or prompts. Experimental results demonstrate that MDDM offers notable advantages in terms of accuracy, controllability, practicality, and security. With flexible strategies, MDDM can achieve accuracy close to 100% under appropriate settings. Additionally, MDDM demonstrates certain robustness and potential for application in watermarking tasks.} }
Endnote
%0 Conference Paper %T MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models %A Zihao Xu %A Dawei Xu %A Zihan Li %A Chuan Zhang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-xu25ah %I PMLR %P 69832--69848 %U https://proceedings.mlr.press/v267/xu25ah.html %V 267 %X Generative image steganography (GIS) is an emerging technique that conceals secret messages in the generation of images. Compared to GAN-based or flow-based GIS schemes, diffusion model-based solutions can provide high-quality and more diverse images, thus receiving considerable attention recently. However, previous GIS schemes still face challenges in terms of extraction accuracy, controllability, and practicality. To address the above issues, this paper proposes a practical message-driven GIS framework based on diffusion models, called MDDM. Specifically, by utilizing the Cardan grille, we encode messages into Gaussian noise, which serves as the initial input for image generation, enabling users to generate diverse images via controllable prompts without additional training. During the information extraction process, receivers only need to use the pre-shared Cardan grille to perform diffusion inversion and recover the messages without requiring the image generation seeds or prompts. Experimental results demonstrate that MDDM offers notable advantages in terms of accuracy, controllability, practicality, and security. With flexible strategies, MDDM can achieve accuracy close to 100% under appropriate settings. Additionally, MDDM demonstrates certain robustness and potential for application in watermarking tasks.
APA
Xu, Z., Xu, D., Li, Z. & Zhang, C.. (2025). MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:69832-69848 Available from https://proceedings.mlr.press/v267/xu25ah.html.

Related Material