Provably Secure Robust Image Steganography via Cross-Modal Error Correction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qi, Yuang, Chen, Kejiang, Zhao, Na, Yang, Zijin, Zhang, Weiming
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916528321986560
author Qi, Yuang
Chen, Kejiang
Zhao, Na
Yang, Zijin
Zhang, Weiming
author_facet Qi, Yuang
Chen, Kejiang
Zhao, Na
Yang, Zijin
Zhang, Weiming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12206
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Provably Secure Robust Image Steganography via Cross-Modal Error Correction
Qi, Yuang
Chen, Kejiang
Zhao, Na
Yang, Zijin
Zhang, Weiming
Multimedia
Cryptography and Security
Computer Vision and Pattern Recognition
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.
title Provably Secure Robust Image Steganography via Cross-Modal Error Correction
topic Multimedia
Cryptography and Security
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.12206