Provably Secure Robust Image Steganography via Cross-Modal Error Correction
This addresses secure and robust image steganography for social media applications, but it is incremental as it builds on existing autoregressive models and error-correction techniques.
The paper tackles the problem of low-quality and non-robust image steganography by proposing a method that uses autoregressive image generation models and cross-modal error correction, resulting in improved stego quality, embedding capacity, and robustness with provable undetectability.
The rapid development of image generation models has facilitated the widespread dissemination of generated images on social networks, creating favorable conditions for provably secure image steganography. However, existing methods face issues such as low quality of generated images and lack of semantic control in the generation process. To leverage provably secure steganography with more effective and high-performance image generation models, and to ensure that stego images can accurately extract secret messages even after being uploaded to social networks and subjected to lossy processing such as JPEG compression, we propose a high-quality, provably secure, and robust image steganography method based on state-of-the-art autoregressive (AR) image generation models using Vector-Quantized (VQ) tokenizers. Additionally, we employ a cross-modal error-correction framework that generates stego text from stego images to aid in restoring lossy images, ultimately enabling the extraction of secret messages embedded within the images. Extensive experiments have demonstrated that the proposed method provides advantages in stego quality, embedding capacity, and robustness, while ensuring provable undetectability.