%0 Journal Article
%A NIU Shao-zhang
%A WEN Juan
%A XUE Yi-ming
%A ZHOU Xiao-shi
%A ZHOU Xue-jing
%T Text Steganography Based on Image Caption
%D 2018
%R 10.13190/j.jbupt.2018-032
%J Journal of Beijing University of Posts and Telecommunications
%P 7-13
%V 41
%N 6
%X Aiming at the problem of low embedding capacity and poor semantic coherence of text steganography, a text steganographic scheme based on neural image caption is proposed. An encode-decode structure with a combination of long short term memory and convolution neural network is used to model the joint probability distributions between image features and the descriptive sentences. Two methods with different sampling process are designed from the perspectives of sharing and non-sharing models. Experimental results show that the proposed model can achieve high embedding capacity and desirable text quality. This scheme belongs to "carrier-free" steganography and has good security.
%U https://journal.bupt.edu.cn/EN/10.13190/j.jbupt.2018-032