RIHNet: A Robust Image Hiding Method for JPEG Compression

Xin Jin, Zien Cheng, Qian Jiang, Wei-Ping Ding, Yunyun Dong, Liwen Wu, Shengfa Miao

Abstract: Image hiding is a task that embeds secret images in digital images without being detected. The performance of image hiding has been greatly improved by using the invertible neural network. However, current image hiding methods are less robust in face of JPEG compression. The secret image cannot be extracted from stego image after JPEG compression of stego image. Some methods show good robustness for some certain JPEG compression quality factors, but poor robustness for other common JPEG compression quality factors. We propose an image hiding network (RIHNet) that is robust to all common JPEG compression quality factors. First of all, we redesign the loss function, thus the secret image is hidden as much as possible to the area that is less possible to be changed after JPEG compression. Secondly, we design the classifier which can help the model to select the extractor according to the range of JPEG compression degree. Finally, we improve the interval robustness of the secret image extraction through the design of the denoising module. Experimental results show that our method outperforms other state-of-the-art methods on PSNR and SSIM values of the recovered secret image and the stego image in face of common JPEG compression.