An End-to-End Robust Video Steganography Model Based on a Multi-Scale Neural Network

Abstract

The purpose of video steganography is to hide messages in the video file and prevent them from being detected, and finally the secret message can be extracted completely at the receiver. In this paper, an end-to-end video steganography based on GAN and multi-scale deep learning network is proposed, which consists of the encoder, decoder and discriminator. However, in the transmission process, videos will inevitably be encoded. Thus, a noise layer is introduced between the encoder and the decoder, which makes the model able to resist popular video compressions. Experimental results show that the proposed end-to-end steganography has achieved high visual quality, large embedding capacity, and strong robustness. Moreover, the proposed method performances better compared to the latest end-to-end video steganography.