Efficient U-Shape Invertible Neural Network for Image Steganography

Le Zhang, Tong Li, Yao Lu, Mixiao Hou, Guangming Lu

Abstract

Currently, it is challenging to recover high-quality secret images from highly secure stego images while maintaining a limited computational cost for image steganography. This paper proposes an Efficient U-shape Invertible Neural Network (EUIN-Net) for image steganography. Due to the gradual fusion and separation properties of the U-shape invertible mechanism, our EUIN-Net comprehensively couples and decouples the secret-cover information on different scales and depths. Besides, using the skip connections between each pair of U-shape invertible blocks, the long-range dependency can be retrieved. Such above two factors can drive our EUIN-Net to promote the quality of both stego and revealed secret images. Furthermore, the shared and multi-scale characteristics of the U-shaped invertible blocks during the hiding and revealing stages contribute to significant reductions of our EUIN-Net in the model size and Flops. Extensive experiments demonstrate that the proposed EUIN-Net is efficient and can achieve state-of-the-art performances for image steganography.
BibTeX
@inproceedings{zhang2024efficient,
  author = {Le Zhang and Tong Li and Yao Lu and Mixiao Hou and Guangming Lu},
  title = {{Efficient U-Shape Invertible Neural Network for Image Steganography}},
  booktitle = {ICME},
  year = {2024},
  doi = {10.1109/icme57554.2024.10687784},
}

Loading related content...

Figure