《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (6): 1730-1735.DOI: 10.11772/j.issn.1001-9081.2022060953

• CCF第37届中国计算机应用大会 (CCF NCCA 2022) • 上一篇    下一篇

基于风格迁移过程的彩色图像信息隐藏算法

杨盼1,2, 张敏情1,2(), 葛虞1,2, 狄富强1,2, 张英男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:2022-07-02 修回日期:2022-08-12 接受日期:2022-08-16 发布日期:2022-09-23 出版日期:2023-06-10
  • 通讯作者: 张敏情
  • 作者简介:杨盼(1994—),男,河南洛阳人,硕士研究生,主要研究方向:信息隐藏、深度学习
    葛虞(1998—),女,河北秦皇岛人,硕士研究生,主要研究方向:信息隐藏、信息安全
    狄富强(1990—),男,陕西西安人,讲师,博士,主要研究方向:信息隐藏、信息安全
    张英男(1990—),男,陕西西安人,副教授,博士,主要研究方向:信息隐藏、信息安全。
  • 基金资助:
    国家自然科学基金资助项目(61872384);武警工程大学基础前沿研究基金资助项目(WJY202012)

Color image information hiding algorithm based on style transfer process

Pan YANG1,2, Minqing ZHANG1,2(), Yu GE1,2, Fuqiang DI1,2, Yingnan ZHANG1,2   

  1. 1.College of Cryptographic Engineering,Engineering University of PAP,Xi’an Shaanxi 710086,China
    2.Key Laboratory of PAP for Network and Information Security (Engineering University of PAP),Xi’an Shaanxi 710086,China
  • Received:2022-07-02 Revised:2022-08-12 Accepted:2022-08-16 Online:2022-09-23 Published:2023-06-10
  • Contact: Minqing ZHANG
  • About author:YANG Pan, born in 1994, M. S. candidate. His research interests include information hiding, deep learning.
    GE Yu, born in 1998, M. S. candidate. Her research interests include information hiding, information security.
    DI Fuqiang, born in 1990, Ph. D., lecturer. His research interests include information hiding, information security.
    ZHANG Yingnan, born in 1990, Ph. D., associate professor. His research interests include information hiding, information security.
  • Supported by:
    National Natural Science Foundation of China(61872384);Basic Frontier Research Fund of Engineering University of PAP(WJY202012)

摘要:

针对基于神经风格迁移的信息隐藏算法没有解决彩色图像的嵌入这一问题,提出了一种基于风格迁移过程的彩色图像信息隐藏算法。首先,利用卷积神经网络(CNN)特征提取的优势,分别提取载体图像的语义信息、风格图像的风格信息以及彩色图像的特征信息;然后,将图像的语义内容和不同风格融合在一起;最后,在通过解码器对载体图像进行风格迁移的同时完成彩色图像的嵌入。实验结果表明,所提算法可以将秘密图像有效融入到生成的风格化图像中,使得秘密信息嵌入行为与风格变换的行为不可区分,在保持算法安全性的前提下,所提算法的隐藏容量提高到24 bpp,峰值信噪比(PSNR)和结构相似性(SSIM)的平均值分别达到了25.29 dB和0.85,有效解决了彩色图像的嵌入问题。

关键词: 信息隐藏, 神经网络, 风格迁移, 高容量, 图像质量

Abstract:

To solve the problem that information hiding algorithms based on neural style transfer do not solve the embedding problem of color images, a color image information hiding algorithm based on style transfer process was proposed. Firstly, the advantages of feature extraction of Convolutional Neural Network (CNN) were utilized to extract the semantic information of the carrier image, the style information of the style image and the feature information of the color image, respectively. Then, the semantic content of images and different styles were fused together. Finally the embedding of color image was completed while performing the style transfer of the carrier image through the decoder. Experimental results show that the proposed algorithm can integrate the secret image into the generated stylized image effectively, making the secret information embedding behavior indistinguishable from the style change behavior. Under the premise of maintaining the security of the algorithm, the proposed algorithm has the hiding capacity increased to 24 bpp, and the average values of Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM) reached 25.29 dB and 0.85 respectively, thereby solving the color image embedding problem effectively.

Key words: information hiding, neural network, style transfer, high capacity, image quality

中图分类号: