A High-Capacity Steganography Algorithm Based on Adaptive Frequency Channel Attention Networks

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 20; p. 7844
• Main Authors: Zhang, Shanqing, Li, Hui, Li, Li, Lu, Jianfeng, Zuo, Ziqian
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 15.10.2022; MDPI
• Subjects: Adaptive algorithms; Algorithms; attention mechanism; Datasets; Deep learning; Digital imaging; discrete cosine transform; Feature selection; Frequency domain analysis; generative adversarial networks; Image quality; image steganography; Methods; Multimedia communications; Neural networks; Steganography; Wavelet transforms
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22207844

Deep learning has become an essential technique in image steganography. Most of the current deep-learning-based steganographic methods process digital images in the spatial domain. There are problems such as limited embedding capacity and unsatisfactory visual quality. To improve capacity-distortion performance, we develop a steganographic method from the frequency-domain perspective. We propose a module called the adaptive frequency-domain channel attention network (AFcaNet), which makes full use of the frequency features in each channel by a fine-grained manner of assigning weights. We apply this module to the state-of-the-art SteganoGAN, forming an Adaptive Frequency High-capacity Steganography Generative Adversarial Network (AFHS-GAN). The proposed neural network enhances the ability of high-dimensional feature extraction through overlaying densely connected convolutional blocks. In addition to this, a low-frequency loss function is introduced as an evaluation metric to guide the training of the network and thus reduces the modification of low-frequency regions of the image. Experimental results on the Div2K dataset show that our method has a better generalization capability compared to the SteganoGAN, with substantial improvement in both embedding capacity and stego-image quality. Furthermore, the embedding distribution of our method in the DCT domain is more similar to that of the traditional method, which is consistent with the prior knowledge of image steganography.