《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (1): 169-175.DOI: 10.11772/j.issn.1001-9081.2021112035

所属专题： 网络空间安全

• 网络空间安全 • 上一篇    下一篇

基于深度卷积生成对抗网络的半生成式视频隐写方案

林洋平1, 刘佳1, 陈培1, 张明书1,2, 杨晓元1,2   

  1. 1.武警工程大学 密码工程学院，西安 710086
    2.网络与信息安全武警部队重点实验室（武警工程大学），西安 710086
  • 收稿日期:2021-12-02 修回日期:2022-05-18 发布日期:2023-01-12
  • 作者简介:林洋平（1998—），男，四川绵阳人，硕士研究生，主要研究方向：信息隐藏；刘佳（1982—），男，河南汝州人，副教授，博士，主要研究方向：深度学习、信息隐藏 email：liujia1022@gmail.com；陈培（1998—），男，福建莆田人，硕士研究生，主要研究方向：信息隐藏；张明书（1978—），男，河南开封人，副教授，博士，主要研究方向：信息安全；杨晓元（1959—），男，湖南湘潭人，教授，硕士，主要研究方向：信息安全、密码学；
  • 基金资助:
    国家自然科学基金资助项目（61872384）；武警工程大学科研创新基金资助项目（KYGG201904）。

Semi-generative video steganography scheme based on deep convolutional generative adversarial net

LIN Yangping1, LIU Jia1, CHEN Pei1, ZHANG Mingshu1,2, YANG Xiaoyuan1,2   

  1. 1.College of Cryptography Engineering， Engineering University of PAP， Xi’an Shaanxi 710086， China
    2.Key Laboratory of Network and Information Security of PAP （Engineering University of PAP）， Xi’an Shaanxi 710086， China
  • Received:2021-12-02 Revised:2022-05-18 Online:2023-01-12
  • Contact: LIU Jia， born in 1982， Ph. D.， associate professor. His research interests include deep learning， information hiding.
  • About author:LIN Yangping， born in 1998， M. S. candidate. His research interests include information hiding；CHEN Pei， born in 1998， M. S. candidate. His research interests include information hiding；ZHANG Mingshu， born in 1978， Ph. D.， associate professor. His research interests include information security；YANG Xiaoyuan， born in 1959， M. S.， professor. His research interests include information security， cryptography；
  • Supported by:
    This work is partially supported by National Natural Science Foundation of China （61872384）， Scientific Research and Innovation Fund of Engineering University of PAP （KYGG201904）.

RichHTML

PDF

摘要： 生成式隐写通过生成足够自然或真实的含密样本来隐藏秘密消息，是信息隐藏方向的研究热点，但目前在视频隐写领域的研究还比较少。结合数字化卡登格的思想，提出一种基于深度卷积生成对抗网络（DCGAN）的半生成式视频隐写方案。该方案中，设计了基于DCGAN的双流视频生成网络，用来生成视频的动态前景、静态后景与时空掩模三个部分，并以随机噪声驱动生成不同的视频。方案中的发送方可设定隐写阈值，在掩模中自适应地生成数字化卡登格，并将其作为隐写与提取的密钥；同时以前景作为载体，实现信息的最优嵌入。实验结果表明，该方案生成的含密视频具有良好的视觉质量，Frechet Inception距离（FID）值为90，且嵌入容量优于现有的生成式隐写方案，最高可达0.11 bpp，能够更高效地传输秘密消息。

关键词: 视频隐写, 半生成式, 深度学习, 深度卷积生成对抗网络, 对抗性训练, 数字化卡登格

Abstract: Generative steganography hides secret messages by generating sufficiently natural or true samples with secret，which is a hot research topic in information hiding， but there is little research in the field of video steganography. Combined with the idea of digital Cardan grille， a semi-generative video steganography scheme based on Deep Convolutional Generative Adversarial Net （DCGAN） was proposed. In this scheme， a dual-stream video generation network based on DCGAN was designed to generate three parts of videos： dynamic foreground， static background and spatio-temporal mask， and different videos were produced by the generation network driven by random noise. The sender in this scheme was able to set the steganography threshold and adaptively generate a digital Cardan grille in the mask， then the obtain digital cardan grille was used as the key for steganography and extraction； at same time， with the foreground as the carrier， the optimal embedding of information was realized. Experimental results show that the video-with-secret generated by the proposed scheme has good visual quality， with a Frechet Inception Distance score （FID） of 90， and the embedding capacity of the scheme is better than those of the existing generative steganography schemes， up to 0.11 bpp. It can be seen that the proposed scheme can transmit secret messages more efficiently.

Key words: video steganography, semi-generative, deep learning, Deep Convolutional Generative Adversarial Net (DCGAN), adversarial training, Digital Cardan Grille (DCG)

中图分类号: 

版权所有 © 2021 四川计算机应用杂志社有限公司
蜀ICP备 05010208 号-3　新出网证(川)字026号
技术支持：北京玛格泰克科技发展有限公司
访问总数：
今日访问：