Invisible Steganography via Generative Adversarial Networks
arXiv:1807.08571
Abstract
Nowadays, there are plenty of works introducing convolutional neural networks (CNNs) to the steganalysis and exceeding conventional steganalysis algorithms. These works have shown the improving potential of deep learning in information hiding domain. There are also several works based on deep learning to do image steganography, but these works still have problems in capacity, invisibility and security. In this paper, we propose a novel CNN architecture named as \isgan to conceal a secret gray image into a color cover image on the sender side and exactly extract the secret image out on the receiver side. There are three contributions in our work: (i) we improve the invisibility by hiding the secret image only in the Y channel of the cover image; (ii) We introduce the generative adversarial networks to strengthen the security by minimizing the divergence between the empirical probability distributions of stego images and natural images. (iii) In order to associate with the human visual system better, we construct a mixed loss function which is more appropriate for steganography to generate more realistic stego images and reveal out more better secret images. Experiment results show that ISGAN can achieve start-of-art performances on LFW, Pascal VOC2012 and ImageNet datasets.
arXiv comment13 pages, 7 figures
References in corpus (6)
- Improved Techniques for Training GANs
- Large-scale JPEG steganalysis using hybrid deep-learning framework
- Generating Steganographic Images via Adversarial Training
- Spatial Image Steganography Based on Generative Adversarial Network
- SSGAN: Secure Steganography Based on Generative Adversarial Networks
- End-to-end Trained CNN Encode-Decoder Networks for Image Steganography