基于可逆机制的端到端单阶段数字水印算法
作者:
基金项目:

北京市教委科技一般项目(KM202410015001); 北京印刷学院校级项目(Ea202302, 27170123033, Ea202301)


End-to-end One-stage Digital Watermarking Algorithm Based on Invertible Mechanisms
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [26]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    数字水印算法因其在版权保护、内容认证、数据隐藏等领域的重要应用价值而受到广泛关注. 在实际应用中, 嵌入水印的图像往往会遭受图像扭曲、锐化模糊等可微噪声的影响, 同时也会面临JPEG压缩、传输错误等不可微噪声的干扰. 现有研究多集中于单一噪声环境下的方案设计, 或者尝试使用可导模型来近似模拟不可微噪声, 这些方法在一定程度上限制了水印算法的鲁棒性. 针对这一问题, 本文提出了一种基于可逆神经网络的端到端单阶段数字水印方案. 该方案利用可逆神经网络模拟不可微噪声, 提高了算法对于实际噪声环境的适应性和鲁棒性. 与现有算法相比, 本算法在多噪声叠加情况下峰值信噪比(PSNR)提高了3.12 dB, 平均提取精度(ACC)提高了35.36%.

    Abstract:

    Digital watermarking algorithms attract widespread attention due to their important application value in the fields of copyright protection, content authentication, and data hiding. In practical applications, images with embedded watermarks are often affected by differentiable noises such as image distortion and sharpening blurring. At the same time, they also face interference from non-differentiable noises such as JPEG compression and transmission errors. Existing studies mostly focus on scheme design in a single noise environment, or attempt to use differentiable models to approximately simulate non-differentiable noises. These methods limit the robustness of watermarking algorithms to a certain extent. To solve this problem, this study proposes an end-to-end one-stage digital watermarking scheme based on an invertible neural network. The scheme uses an invertible neural network to simulate non-differentiable noise, enhancing the algorithm’s adaptability and robustness to actual noisy environments. Compared with existing algorithms, this algorithm improves the peak signal-to-noise ratio (PSNR) by 3.12 dB and the average extraction accuracy (ACC) by 35.36% in the case of multiple noise superposition.

    参考文献
    [1] van Schyndel RG, Tirkel AZ, Osborne CF. A digital watermark. Proceedings of the 1st International Conference on Image Processing. Austin: IEEE, 1994. 86–90.
    [2] Hsu CT, Wu JL. Hidden digital watermarks in images. IEEE Transactions on Image Processing, 1999, 8(1): 58–68.
    [3] Guo HP, Georganas ND. Digital image watermarking for joint ownership verification without a trusted dealer. Proceedings of the 2003 International Conference on Multimedia and Expo. Baltimore: IEEE, 2003. II–497.
    [4] Hamidi M, Haziti ME, Cherifi H, et al. Hybrid blind robust image watermarking technique based on DFT-DCT and Arnold transform. Multimedia Tools and Applications, 2018, 77(20): 27181–27214.
    [5] 夏道勋, 王林娜, 宋允飞, 等. 深度神经网络模型数字水印技术研究进展综述. 科学技术与工程, 2023, 23(5): 1799–1811.
    [6] Mun SM, Nam SH, Jang HU, et al. A robust blind watermarking using convolutional neural network. arXiv: 1704.03248, 2017.
    [7] Mun SM, Nam SH, Jang H, et al. Finding robust domain from attacks: A learning framework for blind watermarking. Neurocomputing, 2019, 337: 191–202.
    [8] Ahmadi M, Norouzi A, Karimi N, et al. ReDMark: Framework for residual diffusion watermarking based on deep networks. Expert Systems with Applications, 2020, 146: 113157.
    [9] Fang H, Jia ZY, Qiu YP, et al. De-END: Decoder-driven watermarking network. IEEE Transactions on Multimedia, 2023, 25: 7571–7581.
    [10] Fang H, Jia ZY, Ma ZH, et al. PIMoG: An effective screen-shooting noise-layer simulation for deep-learning-based watermarking network. Proceedings of the 30th ACM International Conference on Multimedia. Barcelona: ACM, 2022. 2267–2275.
    [11] Cao F, Wang TJ, Guo DD, et al. Screen-shooting resistant image watermarking based on lightweight neural network in frequency domain. Journal of Visual Communication and Image Representation, 2023, 94: 103837.
    [12] Tang ZW, Chai XL, Lu Y, et al. An end-to-end screen shooting resilient blind watermarking scheme for medical images. Journal of Information Security and Applications, 2023, 76: 103547.
    [13] Cao F, Guo DD, Wang TJ, et al. Universal screen-shooting robust image watermarking with channel-attention in DCT domain. Expert Systems with Applications, 2024, 238: 122062.
    [14] Dinh L, Krueger D, Bengio Y. Nice: Non-linear independent components estimation. arXiv:1410.8516, 2014.
    [15] Guan ZY, Jing JP, Deng X, et al. DeepMIH: Deep invertible network for multiple image hiding. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 372–390.
    [16] Luo YJ, Zhou TQ, Liu F, et al. IRWArt: Levering watermarking performance for protecting high-quality artwork images. Proceedings of the 2023 ACM Web Conference. Austin: ACM, 2023. 2340–2348.
    [17] Fang H, Qiu YP, Chen KJ, et al. Flow-based robust watermarking with invertible noise layer for black-box distortions. Proceedings of the 37 AAAI Conference on Artificial Intelligence. Washington: AAAI Press, 2023. 5054–5061.
    [18] Zhu JR, Kaplan R, Johnson J, et al. HiDDeN: Hiding data with deep networks. Proceedings of the 15th European Conference on Computer Vision (ECCV). Milan: Springer, 2018. 657–672.
    [19] Jia ZY, Fang H, Zhang WM. MBRS: Enhancing robustness of DNN-based watermarking by mini-batch of real and simulated JPEG compression. Proceedings of the 29th ACM International Conference on Multimedia. ACM, 2021. 41–49.
    [20] Fang H, Jia ZY, Zhou H, et al. Encoded feature enhancement in watermarking network for distortion in real scenes. IEEE Transactions on Multimedia, 2023, 25: 2648–2660.
    [21] Ma R, Guo MX, Hou Y, et al. Towards blind watermarking: Combining invertible and non-invertible mechanisms. Proceedings of the 30th ACM International Conference on Multimedia. Lisboa: ACM, 2022. 1532–1542.
    [22] 段恒利, 梁晓燕. 基于DCT域JPEG图像压缩算法的研究与设计. 通信与信息技术, 2023(6): 10–12.
    [23] 史艳琼, 王昌文, 卢荣胜, 等. 基于低秩稀疏矩阵分解和离散余弦变换实现多聚焦图像融合的算法. 激光与光电子学进展, 2024, 61(10): 1037010.
    [24] 刘涤. 基于离散余弦变换的数字水印算法研究. 电脑编程技巧与维护, 2023(9): 138–140.
    [25] Liu Y, Guo MX, Zhang J, et al. A novel two-stage separable deep learning framework for practical blind watermarking. Proceedings of the 27th ACM International Conference on Multimedia. Nice: ACM, 2019. 1509–1517.
    [26] Huang JT, Luo T, Li L, et al. ARWGAN: Attention-guided robust image watermarking model based on GAN. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 5018417.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

胡子寒,林立霞,白少杰,曹鹏.基于可逆机制的端到端单阶段数字水印算法.计算机系统应用,2025,34(3):201-209

复制
分享
文章指标
  • 点击次数:59
  • 下载次数: 494
  • HTML阅读次数: 2
  • 引用次数: 0
历史
  • 收稿日期:2024-08-09
  • 最后修改日期:2024-09-19
  • 在线发布日期: 2025-01-16
文章二维码
您是第10782479位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号