Abstract:Video steganography is a art of covert communication which uses videos as cover media. In order to solve the problem of having difficulty generating the optimal modified probability matrix in the video steganography, and guarantee remarkable security of information transmission, a GAN(Generative Adversarial Network)-based video steganography algorithm is proposed. There are two generative adversarial networks that generate the original cover and the modified probability map respectively. The first can generate the static background, dynamic foreground and mask. In order to improve the content adaptability of the modified probability map, the foreground is the input of generator in the second, it uses the Tanh-simulator function, fit the optimal embedding function to promote the back propagation of the gradient. The steganalyzer based on the 3D convolutional network is used as its opponent, the discriminator, and the game training is carried out with the generator to improve the performance on resisting steganalysis. The experimental results show that the video generation module can not only generate realistic videos and the generated foreground information, but symbolizes the spatiotemporal feature information. With the embedding rate of 0.05 bpc, 0.1 bpc, 0.3 bpc, the security performance of our proposed algorithm resisting the SCRM steganalysis increases by 0.65%~3.26% than the classic S-UNIWARD algorithm.