Deep learning for steganalysis based on filter diversity selection  

作　　者：Kai ZHONG Guorui FENG Liquan SHEN Jun LUO 

机构地区：[1]Shanghai Institute for Advanced Communication and Data Science,Shanghai University,Shanghai 200444,China [2]School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China [3]3School of Mechatronic Engineering and Automation,Shanghai University,Shanghai 200444,China

出　　处：《Science China(Information Sciences)》2018年第12期192-194,共3页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China (Grants Nos. U1536109, 61671282, 61373151, 61525305)

摘　　要：Dear editor,Steganography is an important method of covert communication. Steganalysis, an advanced antisteganographic technique can detect steganographic behavior and even reveal the stego key in a certain steganographic method [1]. Steganalysis includes specialized steganalysis [2] and universal steganalysis [3]. This study focuses on feature extraction [3] and feature post-processing [4].

关 键 词：HPF Deep learning for steganalysis based on filter diversity selection 

分 类 号：N[自然科学总论]