PRIS: Practical robust invertible network for image steganography

September 24, 2023 ยท Entered Twilight ยท ๐Ÿ› Engineering applications of artificial intelligence

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: DiffJPEG.py, calculate_PSNR_SSIM.py, config.py, datasets.py, main.py, model.py, modules, readme.md, requirements.txt, result.txt, util.py, viz.py

Authors Hang Yang, Yitian Xu, Xuhua Liu, Xiaodong Ma arXiv ID 2309.13620 Category cs.CV: Computer Vision Cross-listed cs.AI, cs.CR Citations 43 Venue Engineering applications of artificial intelligence Repository https://github.com/yanghangAI/PRIS โญ 46 Last Checked 1 month ago
Abstract
Image steganography is a technique of hiding secret information inside another image, so that the secret is not visible to human eyes and can be recovered when needed. Most of the existing image steganography methods have low hiding robustness when the container images affected by distortion. Such as Gaussian noise and lossy compression. This paper proposed PRIS to improve the robustness of image steganography, it based on invertible neural networks, and put two enhance modules before and after the extraction process with a 3-step training strategy. Moreover, rounding error is considered which is always ignored by existing methods, but actually it is unavoidable in practical. A gradient approximation function (GAF) is also proposed to overcome the undifferentiable issue of rounding distortion. Experimental results show that our PRIS outperforms the state-of-the-art robust image steganography method in both robustness and practicability. Codes are available at https://github.com/yanghangAI/PRIS, demonstration of our model in practical at http://yanghang.site/hide/.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision