Generative Image Steganography Based on Text-to-Image Multimodal Generative Model
- 1 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (9) , 8907-8916
Abstract
Image steganography, the technique of hiding secret messages within images, has recently advanced with generative image steganography, which hides messages during image creation. However, current generative steganography methods often face criticism for their low extraction accuracy and poor robustness—particularly their vulnerability to JPEG compression. To address these challenges, we propose a novel generative image steganography method based on the text-to-image multimodal generative model (StegaMGM). StegaMGM utilizes the initial random normalization distribution in the generative process of latent diffusion models (LDMs), the secret message is hidden in the generated image through message sampling, ensuring it follows the same probability distribution as typical image generative. The content of the stego image can also be controlled through the prompts. On the receiver side, using the shared prompt and diffusion inversion, can extract secret message with high accuracy. In the experimental section, we conducted detailed experiments to demonstrate the advantages of our proposed StegaMGM framework in extraction accuracy, resistance to JPEG compression, and security.Keywords
Funding Information
- Natural Science Foundation of China (U22B2047, 62376148)
- Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission (22CGA46)
This publication has 37 references indexed in Scilit:
- Robust Invertible Image Steganography2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Image Disentanglement Autoencoder for Steganography without Embedding2022
- Large-capacity Image Steganography Based on Invertible Neural Networks2021
- An improved steganography without embedding based on attention GANPeer-to-Peer Networking and Applications, 2021
- Coverless steganography based on image retrieval of DenseNet features and DWT sequence mappingKnowledge-Based Systems, 2020
- Research on Coverless Text Steganography Based on Single Bit RulesJournal of Physics: Conference Series, 2019
- Provably Secure Generative Steganography Based on Autoregressive Model2019
- A Novel Image Steganography Method via Deep Convolutional Generative Adversarial NetworksIEEE Access, 2018
- Using High-Dimensional Image Models to Perform Highly Undetectable Steganography2010