###
Journal of Software:2021.32(2):551-578

基于深度学习的图像隐写分析综述
陈君夫,付章杰,张卫明,程旭,孙星明
(南京信息工程大学 计算机与软件学院, 江苏 南京 210044;南京信息工程大学 计算机与软件学院, 江苏 南京 210044;鹏城实验室, 广东 深圳 518055;中国科学技术大学 信息科学技术学院, 安徽 合肥 230026)
Review of Image Steganalysis Based on Deep Learning
CHEN Jun-Fu,FU Zhang-Jie,ZHANG Wei-Ming,CHENG Xu,SUN Xing-Ming
(School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China;School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China;Peng Cheng Laboratory, Shenzhen 518055, China;School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China)
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 1592   Download 1430
Received:May 30, 2020    Revised:July 10, 2020
> 中文摘要: 隐写术及隐写分析是信息安全领域研究热点之一.隐写术的滥用造成许多安全隐患,如非法分子利用隐写进行隐蔽通信完成恐怖袭击.传统隐写分析方法的设计需要大量先验知识,而基于深度学习的隐写分析方法利用网络强大的表征学习能力自主提取图像异常特征,大大减少了人为参与,取得了较好的研究效果.为了促进基于深度学习的隐写分析方法研究,对目前隐写分析领域的主要方法和突破性工作进行了分析与总结.首先,比较了传统隐写分析方法与基于深度学习的隐写分析方法的差异;然后根据训练方式的不同,将基于深度学习的隐写分析模型分为两类——半学习隐写分析模型与全学习隐写分析模型,详细介绍了基于深度学习的各类隐写分析网络结构与检测效果;其次,分析和总结了对抗样本对深度学习安全带来的挑战,并阐述了基于隐写分析的对抗样本检测方法;最后,总结了现有基于深度学习的隐写分析模型存在的优缺点,并探讨了基于深度学习的隐写分析模型的发展趋势.
Abstract:Steganography and steganalysis are one of the research hotspots in the field of information security. The abuse of steganography has caused many potential safety hazards. For example, illegal elements use steganography for covert communications to carry out terrorist attacks. The design of traditional steganalysis methods requires a large amount of prior knowledge, and the steganalysis methods based on deep learning use the powerful representation learning ability of the network to autonomously extract abnormal image features, which greatly reduces human participation and achieves good results. To promote the research of steganalysis technology based on deep learning, this study analyzes and summarizes the main methods and work in the field of steganalysis. Firstly, this study analyzes and compares the differences between traditional steganalysis and deep learning-based steganalysis. Furthermore, according to the different training methods, the steganalysis models based on deep learning are divided into two categories: semi-learning steganalysis model and full-learningsteganalysis model. The network structure and detection effect of various types of steganalysis based on deep learning are introduced in detail. In addition, the challenges that the adversarial samples pose to deep learning security are analyzed and summarized, the detection method of adversarial samples is expounded based on steganalysis. Finally, this study summarizes the pros and cons of existing steganalysis models based on deep learning and discusses its development trends.
文章编号:     中图分类号:    文献标志码:
基金项目:国家重点研发计划(2018YFB1003205);国家自然科学基金(U1836110,U1836208,61802058,61911530397) 国家重点研发计划(2018YFB1003205);国家自然科学基金(U1836110,U1836208,61802058,61911530397)
Foundation items:National Key Research and Development Program of China (2018YFB1003205); National Natural Science Foundation of China (U1836110, U1836208, 61802058, 61911530397)
Reference text:

陈君夫,付章杰,张卫明,程旭,孙星明.基于深度学习的图像隐写分析综述.软件学报,2021,32(2):551-578

CHEN Jun-Fu,FU Zhang-Jie,ZHANG Wei-Ming,CHENG Xu,SUN Xing-Ming.Review of Image Steganalysis Based on Deep Learning.Journal of Software,2021,32(2):551-578