Coding Efficiency Preserving Steganography Based on HEVC Steganographic Channel Model

Steganographic Channel Model (SCM) is hard to build for different steganography algorithms in different embedding domains. Thus, theoretical analysis for some important factors in steganography, such as capacity, distortion, is hard to obtain. In this paper, to avoid introducing significant distortion into HEVC video file, a novel HEVC SCM is presented and analyzed. It is firstly proposed that the distortion optimization method in this SCM should be applied on coding efficiency instead of visual quality. According to this conclusion, a novel coding efficiency preserving steganography algorithm based on Prediction Units (PUs) is proposed for HEVC videos. The intra prediction modes of candidate PUs are taken as cover. This algorithm was tested on the dataset consisting of 17,136 HD sequences. The Experimental results prove the correctness of the previous conclusion and the practicability of the proposed channel model, and show that our algorithm outperforms the existing HEVC steganography algorithm in capacity and perceptibility.