基于自适应注意力机制与SimSiam框架的图像水印研究

诸葛斌; 陈莹莹; 王冰雁; 董黎刚; 蒋献

doi:10.11959/j.issn.1000-0801.DXKX250688

您当前的位置：

首页 >

文章列表页 >

基于自适应注意力机制与SimSiam框架的图像水印研究

更新时间：2026-06-16

- 基于自适应注意力机制与SimSiam框架的图像水印研究
- Research on Image Watermarking Based on Adaptive Attention Mechanism and SimSiam Framework
- 电信科学 2026年
- 作者机构：
  
  浙江工商大学信息与电子工程学院，浙江杭州 310000
- 作者简介：
  
  诸葛斌，1976年，男，博士，浙江工商大学，教授，主要研究方向为医学图像配准与模式识别、互联网技术和云计算。
  陈莹莹，2001年，女，硕士，浙江工商大学，学生，主要研究方向为智慧教育。
  王冰雁，2000年，女，硕士，浙江工商大学，学生，主要研究方向为智慧教育。
  董黎刚，1972年，男，博士，浙江工商大学，教授，浙江工商大学信息与电子工程学院院长，主要研究方向为智慧教育与智慧网络。
  蒋献，1988年，男，博士，浙江工商大学，实验员，主要研究方向为智慧教育与智慧网络。
- 基金信息：
  
  浙江省领雁研发项目(2023C03202);浙江省大学生科技成果推广项目·新苗计划(2025R408B075)
- DOI：10.11959/j.issn.1000-0801.DXKX250688
  中图分类号： TP18
- 收稿：2025-11-28，
  
  修回：2026-02-22，
  
  录用：2026-05-11，
- 稿件说明：
移动端阅览
诸葛斌, 陈莹莹, 王冰雁, 等. 基于自适应注意力机制与SimSiam框架的图像水印研究[J/OL]. 电信科学, 2026.

Zhuge Bin, Chen Yingying, Wang Bingyan, et al. Research on Image Watermarking Based on Adaptive Attention Mechanism and SimSiam Framework[J/OL]. Telecommunications Science, 2026.
诸葛斌, 陈莹莹, 王冰雁, 等. 基于自适应注意力机制与SimSiam框架的图像水印研究[J/OL]. 电信科学, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX250688.

Zhuge Bin, Chen Yingying, Wang Bingyan, et al. Research on Image Watermarking Based on Adaptive Attention Mechanism and SimSiam Framework[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX250688.

摘要

针对智慧教育中高精度图像的版权保护需求，本文提出一种融合自适应注意力机制与SimSiam自监督对比学习的鲁棒盲水印算法。该方法利用自适应注意力在高频纹理区域动态分配嵌入权重，在提升JPEG压缩、随机裁剪等攻击鲁棒性的同时保持较高图像质量。SimSiam模块利用对比学习强化特征一致性，有效抑制攻击带来的差异，突出水印的语义稳定性。实验结果表明，本文方法在JPEG压缩（质量因子50）与50%随机裁剪下均实现100%比特恢复率（BRR），PSNR较传统DCT方法提升15.4%。本研究为智慧教育场景下的教学图像提供了一种兼顾鲁棒性与视觉保真度的版权保护技术路径。

Abstract

To address the copyright protection requirements of high-precision images in smart education

a robust blind watermarking algorithm integrating an adaptive attention mechanism and the SimSiam self-supervised contrastive learning framework was proposed. The adaptive attention mechanism dynamically allocated embedding weights in high-frequency texture regions

thereby enhancing robustness against attacks such as JPEG compression and random cropping while maintaining high image quality. The SimSiam module strengthened feature consistency through contrastive learning

effectively suppressing attack-induced variations and improving the semantic stability of the watermark. Experimental results demonstrated that the proposed method achieved a 100% bit recovery rate (BRR) under JPEG compression (quality factor 50) and 50% random cropping

with a 15.4% improvement in PSNR compared with the traditional DCT-based method. This study provides a copyright protection solution for educational images that balances robustness and visual fidelity in smart education scenarios.

关键词

Keywords

references

Saini , Lalit Kumar and Vishal Shrivastava . “ A Survey of Digital Watermarking Techniques and its Applications .” ArXiv abs/1407.4735 ( 2014 ): n. pag.

Wang Z , Byrnes O , Wang H , et al . Data hiding with deep learning: A survey unifying digital watermarking and steganography [J ] . IEEE Transactions on Computational Social Systems , 2023 , 10 ( 6 ): 2985 - 2999 .

Zhu J. , Kaplan R. , Johnson J. , & Fei-Fei L. ( 2018 ). HiDDeN: Hiding Data With Deep Networks . European Conference on Computer Vision .

Zhong X , Das A , Alrasheedi F , et al . A brief, in-depth survey of deep learning-based image watermarking [J ] . Applied Sciences , 2023 , 13 ( 21 ): 11852 .

Kandi H , Mishra D , Gorthi S R K S . Exploring the learning capabilities of convolutional neural networks for robust image watermarking [J ] . Computers & Security , 2017 , 65 : 247 - 268 .

Fierro-Radilla A , Nakano-Miyatake M , Cedillo-Hernandez M , et al . A robust image zero-watermarking using convolutional neural networks [C ] // 2019 7th International Workshop on Biometrics and Forensics (IWBF) . IEEE , 2019 : 1 - 5 .

Kandi H , Mishra D , Gorthi S R K S . Exploring the learning capabilities of convolutional neural networks for robust image watermarking [J ] . Computers & Security , 2017 , 65 : 247 - 268 .

Qiao T , Ma Y , Zheng N , et al . A novel model watermarking for protecting generative adversarial network [J ] . Computers & Security , 2023 , 127 : 103102 .

Fei J , **a Z , Tondi B , et al . Supervised gan watermarking for intellectual property protection [C ] // 2022 IEEE International Workshop on Information Forensics and Security (WIFS) . IEEE , 2022 : 1 - 6 .

Duan X , Liu J , Zhang E . Efficient image encryption and compression based on a VAE generative model [J ] . Journal of Real-Time Image Processing , 2019 , 16 : 765 - 773 .

Xue D. , Zhou Y. , & Jin W. ( 2017 ). A blind dual-function digital watermarking algorithm for copyright protection and content authentication . 电信科学 , 33 ( 2 ), 79 – 89 . (in Chinese)

Abdalwahid S M J , Hashim W A , Saeed M G , et al . Investigating the Effectiveness of Artificial Intelligence in Watermarking and Steganography for Digital Media Security [C ] // 2024 21st International Multi-Conference on Systems , Signals & Devices (SSD) . IEEE , 2024 : 552 - 561 .

Shih F Y . Digital watermarking and steganography: fundamentals and techniques [M ] . CRC press , 2017 .

Zhu J , Kaplan R , Johnson J , et al . Hidden: Hiding data with deep networks [C ] // Proceedings of the European conference on computer vision (ECCV) . 2018 : 657 - 672 .

Tavakoli A , Honjani Z , Sajedi H . Convolutional neural network-based image watermarking using discrete wavelet transform [J ] . International Journal of Information Technology , 2023 , 15 ( 4 ): 2021 - 2029 .

Mahapatra D , Amrit P , Singh O P , et al . Autoencoder-convolutional neural network-based embedding and extraction model for image watermarking [J ] . Journal of Electronic Imaging , 2023 , 32 ( 2 ): 021604 - 021604 .

Singh H K , Baranwal N , Singh K N , et al . GANMarked: Using Secure GAN for Information Hiding in Digital Images [J ] . IEEE Transactions on Consumer Electronics , 2024 .

Fernandez P , Sablayrolles A , Furon T , et al . Watermarking images in self-supervised latent spaces [C ] // ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . IEEE , 2022 : 3054 - 3058 .

Cong T , He X , Zhang Y . Sslguard: A watermarking scheme for self-supervised learning pre-trained encoders [C ] // Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security . 2022 : 579 - 593 .

Mohammad Moosazadeh and Gholamhossein Ekbatanifard . 2019 . A new DCT-based robust image watermarking method using teaching-learning-Based optimization. J. Inf. Secur . Appl . 47 , C (Aug 2019 ), 28 – 38 . https://doi.org/10.1016/j.jisa.2019.04.001 https://doi.org/10.1016/j.jisa.2019.04.001

Bamatraf , Abdullah et al . “ A New Digital Watermarking Algorithm Using Combination of Least Significant Bit (LSB) and Inverse Bit .” ArXiv abs/1111.6727 ( 2011 ): n. pag.

J. Zhu , R. Kaplan , J. Johnson , and L. Fei-Fei ,“ HiDDeN: Hiding Data With Deep Networks ,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ,Salt Lake City, UT, USA, 2018, pp. 3037 – 3045 .

H. K. Singh and K. R. Ramkumar ,“ Deep watermarking using generative adversarial networks ,” IEEE Transactions on Multimedia ,vol. 22 , no. 12 , pp. 3165 – 3179 , Dec. 2020 .

Dasgupta , Agnibh and Xin Zhong . “ Robust Image Watermarking Based on Cross-Attention and Invariant Domain Learning .” 2023 International Conference on Computational Science and Computational Intelligence (CSCI) ( 2023 ): 1125 - 1132 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于知识追踪机的多特征融合习题推荐模型

FedDACS: 基于分布感知可控采样优化的个性化群体知识迁移

2025年中国通信学会科学技术奖获奖情况分析与思考

基于高阶累积量二维切片谱分析的无人机探测

一种基于证据融合的类不平衡分类方法及其在网络流量识别中的应用