Provably Secure Image Robust Steganography via Cross-modal Error Correction
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (25) · 26354-26362
DOI: 10.1609/aaai.v39i25.34834 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yuang Qi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Qi, Y., Chen, K., Zhao, N., Yang, Z., & Zhang, W. (2025). Provably Secure Image Robust Steganography via Cross-modal Error Correction. Proceedings of the AAAI Conference on Artificial Intelligence, 39(25), 26354-26362. https://doi.org/10.1609/aaai.v39i25.34834
Vancouver
Qi Y, Chen K, Zhao N, Yang Z, Zhang W. Provably Secure Image Robust Steganography via Cross-modal Error Correction. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(25):26354-26362. doi:10.1609/aaai.v39i25.34834
BibTeX
@article{Qi2025,
author = {Qi, Yuang and Chen, Kejiang and Zhao, Na and Yang, Zijin and Zhang, Weiming},
title = {Provably Secure Image Robust Steganography via Cross-modal Error Correction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {25},
pages = {26354--26362},
doi = {10.1609/aaai.v39i25.34834}
}
EUVIMED