No 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-VOC12 and ImageNet datasets.

No abstract

By employing the dissociation energy and the equilibrium bond length for a diatomic molecule as explicit parameters, we generate improved expressions for the well-known Rosen-Morse, Manning-Rosen, Tietz, and Frost-Musulin potential energy functions. It is found that the well-known Tietz potential function that is conventionally defined in terms of five parameters [T. Tietz, J. Chem. Phys. 38, 3036 (1963)] actually only has four independent parameters. It is shown exactly that the Wei [Phys. Rev. A 42, 2524 (1990)] and the well-known Tietz potential functions are the same solvable empirical function. When the parameter h in the Tietz potential function has the values 0, +1, and -1, the Tietz potential becomes the standard Morse, Rosen-Morse, and Manning-Rosen potentials, respectively.