北京航空航天大学学报 ›› 2021, Vol. 47 ›› Issue (11): 2226-2233.doi: 10.13700/j.bh.1001-5965.2021.0179

• 论文 • 上一篇    下一篇

基于多尺度残差卷积网络的HEVC视频隐写分析

张敏1, 李赵红2, 刘金豆2, 张珍珍3   

  1. 1. 中国电信股份有限公司, 北京 100010;
    2. 北京交通大学 电子信息工程学院, 北京 100044;
    3. 北京印刷学院 信息工程学院, 北京 102600
  • 收稿日期:2021-04-07 发布日期:2021-12-04
  • 通讯作者: 张敏 E-mail:zhangmin3@chinatelecom.cn
  • 基金资助:
    北京市教育委员会科研计划(KM202110015004)

Steganalysis for HEVC video based on multi-scale residual convolution network

ZHANG Min1, LI Zhaohong2, LIU Jindou2, ZHANG Zhenzhen3   

  1. 1. China Telecom Corporation Limited, Beijing 100010, China;
    2. School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China;
    3. School of Information Engineering, Beijing Institute of Graphic Communication, Beijing 102600, China
  • Received:2021-04-07 Published:2021-12-04
  • Supported by:
    The Scientific Research Common Program of Beijing Municipal Commission of Education (KM202110015004)

摘要: 图片、语音、视频等多媒体形式的信息交流在网络通信中占有重要地位,同时也有很多非法信息的传播隐匿于此。隐写分析是甄别隐秘信息是否存在的有效手段,提出了一种通用的基于多尺度残差卷积网络的HEVC视频隐写分析算法。网络主体由残差计算、特征提取和二分类3部分构成,其中在特征提取部分针对性地提出了残差卷积层、多尺度残差卷积模块及隐写分析残差块。实验结果表明:所提算法基于视频像素域分析网络的检测率高达99.75%,比传统的手工提取特征方法具有更大的优势。

关键词: 隐写分析, HEVC, 深度学习, 视频, 卷积网络

Abstract: The information exchange, in the forms of pictures, voice, video and other multimedia, plays an important role in network communication, as well as many illegal information disseminations are hidden. Steganalysis is an effective way of detecting secret information. This paper proposes a universal HEVC video steganalysis algorithm based on multi-scale residual convolution network, mainly consisting of residual calculation, feature extraction and binary classification. In the feature extraction part, residual convolution layer, multi-scale residual convolution module and a steganalysis residual block are proposed. Our experimental results show that the detection rate of this method based on video pixel domain analysis network is as high as 99.75%, which has greater advantages than the traditional manual feature extraction methods.

Key words: steganalysis, HEVC, deep learning, video, convolution network

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发