网络与信息安全学报 ›› 2023, Vol. 9 ›› Issue (2): 175-183.doi: 10.11959/j.issn.2096-109x.2023031

• 学术论文 • 上一篇    下一篇

基于传统引导机制的深度鲁棒水印算法

郭学镜, 方毅翔, 赵怡, 张天助, 曾文超, 王俊祥   

  1. 景德镇陶瓷大学机械电子工程学院，江西 景德镇 333000
  • 修回日期:2023-02-01 出版日期:2023-04-25 发布日期:2023-04-01
  • 作者简介:郭学镜（1996- ），男，江西上饶人，景德镇陶瓷大学硕士生，主要研究方向为信息安全与数字图像处理
    方毅翔（1987- ），男，江西景德镇人，景德镇陶瓷大学讲师，主要研究方向为信息安全与数字图像处理
    赵怡（1985- ），女，江西南昌人，景德镇陶瓷大学实验师，主要研究方向为信息安全与数字图像处理
    张天助（1993- ），男，江西上饶人，景德镇陶瓷大学助理讲师，主要研究方向为信息安全与数字图像处理
    曾文超（1996- ），男，湖北宜昌人，景德镇陶瓷大学硕士生，主要研究方向为信息安全与数字图像处理
    王俊祥（1985- ），男，江西景德镇人，景德镇陶瓷大学教授，主要研究方向为信息安全与数字图像处理
  • 基金资助:
    国家自然科学基金(62062044);国家自然科学基金(62063010);江西省科技合作专项重点项目(20212BDH80021);景德镇市级科技计划项目(2020ZDGG004)

Traditional guidance mechanism based deep robust watermarking

Xuejing GUO, Yixiang FANG, Yi ZHAO, Tianzhu ZHANG, Wenchao ZENG, Junxiang WANG   

  1. School of Mechanical and Electronic Engineering, Jingdezhen Ceramic University, Jingdezhen 333000, China
  • Revised:2023-02-01 Online:2023-04-25 Published:2023-04-01
  • Supported by:
    The National Natural Science Foundation of China(62062044);The National Natural Science Foundation of China(62063010);The Science and Technology Cooperation Special Key Project of Jiangxi Province(20212BDH80021);Jingdezhen Municipal Science and Technology Plan Project(2020ZDGG004)

在线阅读

21

pdf下载

88

摘要：

随着网络和多媒体技术的发展，多媒体数据逐渐成为人们获取信息的重要来源，数字媒体逐渐成为版权保护和防伪溯源主战场，版权保护新技术的重要性日益凸显，数字水印技术作为其中一种重要的版权保护手段得到重视。在信息传递过程中，含密数字媒体信息可能会受到噪声和外部干扰攻击，传统鲁棒数字水印技术正是围绕这些问题进行研究。然而，传统的鲁棒数字水印技术对不同类型攻击的综合抵抗能力有待提升。同时，由于其嵌入方式的局限性，传统的鲁棒数字水印算法对不同图像的泛化处理能力较弱。近年来，深度学习由于其强大的自学习能力被广泛应用于鲁棒数字水印技术研究。基于深度网络的鲁棒数字水印算法的初始化通常来源于随机的参数和特征，这会导致生成的模型质量不佳、训练时间过长，甚至无法收敛。结合两者的优点，采用传统的数字水印技术进行引导，兼顾深度网络的学习能力和传统鲁棒数字水印技术特征进行设计，提出一种基于传统引导机制的深度鲁棒数字水印算法。所提算法利用传统的鲁棒数字水印算法生成水印图像，设计的特征构造能够保证传统水印图像的鲁棒性。再利用U-Net结构将传统水印图像融合至深度网络，生成最终的含密图像。实验结果表明，所提算法能够提升含密图像抵抗各种攻击的鲁棒性，并且保证更好的视觉质量。

关键词: 水印技术, 深度网络, 鲁棒水印, U-Net

Abstract:

With the development of network and multimedia technology, multimedia data has gradually become a key source of information for people, making digital media the primary battlefield for copyright protection and anti-counterfeit traceability.Digital watermarking techniques have been widely studied and recognized as important tools for copyright protection.However, the robustness of conventional digital watermarking methods is limited as sensitive digital media can easily be affected by noise and external interference during transmission.Then the existing powerful digital watermarking technology’s comprehensive resistance to all forms of attacks must be enhanced.Moreover, the conventional robust digital watermarking algorithm’s generalizability across a variety of image types is limited due to its embedding method.Deep learning has been widely used in the development of robust digital watermarking systems due to its self-learning abilities.However, current initialization techniques based on deep neural networks rely on random parameters and features, resulting in low-quality model generation, lengthy training times, and potential convergence issues.To address these challenges, a deep robust digital watermarking algorithm based on a traditional bootstrapping mechanism was proposed.It combined the benefits of both traditional digital watermarking techniques and deep neural networks, taking into account their learning abilities and robust characteristics.The algorithm used the classic robust digital watermarking algorithm to make watermarked photos, and the constructed feature guaranteed the resilience of traditional watermarked images.The final dense image was produced by fusing the conventionally watermarked image with the deep network using the U-Net structure.The testing results demonstrate that the technique can increase the stego image’s resistance to various attacks and provide superior visual quality compared to the conventional algorithm.

Key words: watermarking technology, deep network, robust watermarking, U-Net

中图分类号: 

No Suggested Reading articles found!