Xintao Duan

Duan Xintao, Liu Nao

In the past, steganography was to embed text in a carrier, the sender Alice and the recipient Bob share the key, and the text is extracted by Bob through the key. If more information is embedded, the image is easily distorted. In contrast, if there is less embedded information, the image maintains good visual integrity, but does not meet our requirements for steganographic capacity. In this paper, we focus on tackling these challenges and limitations to improve steganographic capacity. An image steganography method based on Fully Convolutional Dense Network(FC-DenseNet) was proposed by us. The hidden network and the extracted network are trained at the same time. The dataset of the deep neural network is derived from various natural images of ImageNet. The experimental results show that the stego-image after steganography and the secret image extracted from stego-imge have a visually good effect, and the stego-image has high capacity and high peak signal to noise ratio. Image-to-image full size hiding is implemented.

Xintao Duan, Haoxian Song

A new coverless image information hiding method based on generative model is proposed, we feed the secret image to the generative model database, and generate a meaning-normal and independent image different from the secret image, then, the generated image is transmitted to the receiver and is fed to the generative model database to generate another image visually the same as the secret image. So we only need to transmit the meaning-normal image which is not related to the secret image, and we can achieve the same effect as the transmission of the secret image. This is the first time to propose the coverless image information hiding method based on generative model, compared with the traditional image steganography, the transmitted image does not embed any information of the secret image in this method, therefore, can effectively resist steganalysis tools. Experimental results show that our method has high capacity, safety and reliability.

Xintao Duan, Haoxian Song, En Zhang et al.

To protect image contents, most existing encryption algorithms are designed to transform an original image into a texture-like or noise-like image, which is, however, an obvious visual sign indicating the presence of an encrypted image, results in a significantly large number of attacks. To solve this problem, in this paper, we propose a new image encryption method to generate a visually same image as the original one by sending a meaning-normal and independent image to a corresponding well-trained generative model to achieve the effect of disguising the original image. This image disguise method not only solves the problem of obvious visual implication, but also guarantees the security of the information.