摘要
现今主流的图像隐写分析方法主要聚焦于设计检测特征,用以提高通用盲检测(universal blind detection,简称UBD)模型的检测准确率,这类检测方法与待测图像无关,难以做到精准检测.在拥有大数据训练资源的前提下,研究了隐写对图像特征的影响,找出了隐写分析与图像特征之间的重要关系,基于此提出了一种为测试样本选择专用训练集的隐写分析方法.以经典的JPEG隐写算法nsF5和主流的JPEG隐写分析特征(CC-PEV、CC-Chen、CF*、DCTR和GFR)为例组织实验,结果表明,该方法的检测准确率高于其他同类方法.
Nowadays,the steganalysis of digital image mainly focuses on the design of steganalysis features to improve the universal blind detection（UBD）model＇s detection accuracy.However it has nothing to do with the testing images and is difficult to achieve high-precision detection.Based on large data training resources,this article studies the influence of steganography on image features to uncover the important relationship between steganalysis and image feature.Furthermore,the article proposes a steganalysis method for testing samples to select specialized training sets.The classical JPEG steganography algorithm nsF5 and the mainstream JPEG steganalysis features,such as CC-PEV,CC-Chen,CF＊,DCTR and GFR,are used as an example to organize the experiments.The results show that the accuracy of this method is higher than that of other similar methods.
作者
张逸为
张卫明
俞能海
ZHANG Yi-Wei;ZHANG Wei-Ming;YU Neng-Hai(School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China;Key Laboratory of Electromagnetic Spatial Information of the Chinese Academy of Sciences （University of Science and Technology of China）, Hefei 230027, China)
出处
《软件学报》
EI
CSCD
北大核心
2018年第4期987-1001,共15页
Journal of Software
基金
国家自然科学基金(U1636201
61572452)~~
关键词
信息隐藏
隐写分析
特定测试样本
高精度
机器学习
information hiding
steganalysis
specific testing sample
high precision
machine learning
