A Generative Method for Steganography by Cover Synthesis with Auxiliary Semantics

作     者：Zhuo Zhang Guangyuan Fu Rongrong Ni Jia Liu Xiaoyuan Yang Zhuo Zhang;Guangyuan Fu;Rongrong Ni;Jia Liu;Xiaoyuan Yang

作者机构：Rocket Force University of EngineeringXi’an 710025China the Key Laboratory of Network and Information Security of PAPEngineering University of PAPXi’an 710086China the Institute of Information ScienceBeijing Jiaotong UniversityBeijing 100044China 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2020年第25卷第4期

页      面：516-527页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0839[工学-网络空间安全] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 081201[工学-计算机系统结构] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(NSFC)(Nos.61872384 and61672090) 

主　　题：information hiding steganography steganography without modification Steganography by Cover Synthesis(SCS) generative adversarial networks 

摘      要：Traditional steganography is the practice of embedding a secret message into an image by modifying the information in the spatial or frequency domain of the cover *** this method has a large embedding capacity,it inevitably leaves traces of rewriting that can eventually be discovered by the *** method of Steganography by Cover Synthesis(SCS)attempts to construct a natural stego image,so that the cover image is not modified;thus,it can overcome detection by a steganographic *** to the difficulty in constructing natural stego images,the development of SCS is *** this paper,a novel generative SCS method based on a Generative Adversarial Network(GAN)for image steganography is *** our method,we design a GAN model called Synthetic Semantics Stego Generative Adversarial Network(SSS-GAN)to generate stego images from secret *** establishing a mapping relationship between secret messages and semantic category information,category labels can generate pseudo-real images via the generative ***,the receiver can recognize the labels via the classifier network to restore the concealed information in *** trained the model on the MINIST,CIFAR-10,and CIFAR-100 image *** show the feasibility of this *** security,capacity,and robustness of the method are analyzed.