LDStega: Practical and Robust Generative Image Steganography based on Latent Diffusion Models
Abstract: Generative image steganography has gained significant attention due to its ability to hide secret data during image generation. However, existing generative image steganography methods still face challenges in terms of controllability, usability, and robustness, making it difficult to apply real-world scenarios. To ensure secure and reliable communication, we propose a practical and robust generative image steganography based on Latent Diffusion Models, called LDStega. LDStega takes controllable condition text as input and designs an encoding strategy in the reverse process of the Latent Diffusion Models to couple latent space generation with data hiding. The encoding strategy selects a sampling interval from a candidate pool of truncated Gaussian distributions guided by secret data to generate the stego latent space. Subsequently, the stego latent space is fed into the Decoder to generate the stego image. The receiver extracts the secret data from the globally Gaussian distribution of the lossy-reconstructed latent space in the reverse process. Experimental results demonstrate that LDStega achieves high extraction accuracy while controllably generating image content and saving the stego image in the widely used PNG and JPEG formats. Additionally, LDStega outperforms state-of-the-art techniques in resisting common image attacks.
Primary Subject Area: [Experience] Multimedia Applications
Secondary Subject Area: [Experience] Multimedia Applications, [Content] Vision and Language
Relevance To Conference: Image steganography is the art and science of hiding secret data within a common image, concealing the fact that a secret exists at all. The more popular the image then the less likely it is to arouse suspicion. Recently, diffusion models have achieved remarkably high-quality image generation, especially Latent Diffusion Models (LDM) have substantially enhanced the speed of image generation by diffusing in latent space. LDM facilitates text-based conditional image generation, which aligns well with our steganography task's need for controllability. Meanwhile, large-scale LDM communities have contributed an extensive collection of freely available open-source tools, which provide a camouflaged environment for steganography. However, how to couple message hiding and image generation in LDM, while the process is also robust to lossy data storage and lossy channel transmission operations, remains a problem. To address this, we propose LDStega, a practical and robust generative image steganography based on LDM. Experimental results demonstrate that LDStega achieves high extraction accuracy while controllably generating image content and saving the stego image in the widely used PNG and JPEG formats. LDStega outperforms state-of-the-art techniques in resisting common image attacks. Therefore, the proposed method enhances the security and practicality of covert communication using multimedia as a cover.
Submission Number: 5197
Loading