Similar articles

Abstract: image steganography algorithms based on deep learning are often trained using either spatial or frequency domain features. It is difficult for features from a single domain to comprehensively express the content of an entire image, which usually leads to poor performance because steganography is commonly a multi-task. To solve this problem, this paper proposes a robust image steganography algorithm based on feature score maps, called the secure and robust image steganography network (SRIS-Net). First, instead of spatial domain steganography, our proposed algorithm utilizes a convolutional neural network to obtain shallow spatial domain features. These features are decomposed by laplace pyramid frequency domain decomposition (LPFDD) to hide secret information in the different frequency sub-bands with a progressive assisted hiding strategy that significantly reduces the influence of the secret information on the cover image, effectively achieving significant invisibility and robust performance. In addition, we propose a global-local embedding module (GLEM) to achieve embedding by considering the overall structure of the image and the local details, and a dual multi-scale aggregation sub-network (DMSubNet) to preform multi-scale reconstruction to improve the quality of the carrier image. For security, we propose a dual-task discriminator structure, while giving a real/fake judgment of the image, which can generate a feature score map of the cover image region of interest (ROI) to guide the embedding module to generate a carrier image with higher imperceptibility and undetectability. Experimental results on the BOSSBase show that our SRIS-Net outperforms other mainstream methods in terms of undetectability and robustness, with more than 9.2 dB and 3.4 dB improvement in visual quality, respectively, and the capacity can be increased up to approximately 72 to 96 bpp.