| Title | Image steganography using texture features and GANs |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Huang, Jinjing, Cheng, Shaoyin, Lou, Songhao, Jiang, Fan |
| Conference Name | 2019 International Joint Conference on Neural Networks (IJCNN) |
| Date Published | jul |
| Keywords | adversarial discriminator, Adversarial training, complex texture regions, convolutional network, cover images, cryptography, cyber physical systems, deep neural networks, encoder-decoder framework, feature extraction, hidden writing, Image Steganography, image texture, invisible perturbations, mean squared error, natural images, pubcrawl, QR code, QR codes, Resiliency, secret information, steganography, stego image distortions, stego images, texture feature, texture features, texture-based loss, truncated layer, varisized images |
| Abstract | As steganography is the main practice of hidden writing, many deep neural networks are proposed to conceal secret information into images, whose invisibility and security are unsatisfactory. In this paper, we present an encoder-decoder framework with an adversarial discriminator to conceal messages or images into natural images. The message is embedded into QR code first which significantly improves the fault-tolerance. Considering the mean squared error (MSE) is not conducive to perfectly learn the invisible perturbations of cover images, we introduce a texture-based loss that is helpful to hide information into the complex texture regions of an image, improving the invisibility of hidden information. In addition, we design a truncated layer to cope with stego image distortions caused by data type conversion and a moment layer to train our model with varisized images. Finally, our experiments demonstrate that the proposed model improves the security and visual quality of stego images. |
| DOI | 10.1109/IJCNN.2019.8852252 |
| Citation Key | huang_image_2019 |
Image steganography using texture features and GANs