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

Published: 01 May 2025, Last Modified: 18 Jun 2025ICML 2025 posterEveryoneRevisionsBibTeXCC BY 4.0
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 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 exact 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 always achieve almost 100\% accuracy. Additionally, MDDM demonstrates certain robustness and exhibits potential for application in watermarking tasks.
Lay Summary: Image steganography is a common method to hide information in images, but traditional methods may not be secure and reliable enough. With the widespread popularity of AI-generated images, generative image steganography could be a future trend. We have constructed a generative image steganography based on a diffusion model, which can generate arbitrary images for arbitrary messages, just like normal image generation. Our method does not require any training and will be beneficial for future steganography research and applications.
Primary Area: Deep Learning->Generative Models and Autoencoders
Keywords: Generative image steganography, Diffusion Models
Submission Number: 10075
Loading