计算机科学 ›› 2024, Vol. 51 ›› Issue (2): 343-351.doi: 10.11896/jsjkx.221200121
黄昌喜, 赵成鑫, 姜骁腾, 凌贺飞, 刘辉
HUANG Changxi, ZHAO Chengxin, JIANG Xiaoteng, LING Hefei, LIU Hui
摘要: 数字水印技术在多媒体保护方面发挥着巨大的作用,实际应用需求的变更推动了数字水印技术的发展。目前,基于深度学习的水印技术在鲁棒性上有了较大的提升,但水印的嵌入基本在空域进行,载体图像的失真仍然比较明显。此外,现有方法在面对摄屏攻击时效果不佳。为解决上述问题,提出了一种抗屏摄攻击的DCT域深度水印方法。该模型由 DCT 层、编码器、解码器和屏摄模拟层组成。 DCT 层将图像的 Y 分量转换为 DCT 域,然后编码器通过端到端训练修改 DCT 系数,将秘密消息嵌入到图像中。这种频域嵌入方法使得水印信息能够分布到图像的整个空间,从而减少了失真效应。此外,还提出了一个噪声层,用于模拟屏摄过程中特殊的摩尔纹和反光效果。训练过程分为两个阶段:在第一阶段,编码器和解码器进行端到端的训练;而在第二阶段,屏摄模拟层和传统的失真攻击被用来增强水印图像,然后使用失真水印图像来进一步优化解码器。大量的实验结果表明,该模型具有较高的透明度和鲁棒性,并且在屏摄鲁棒性方面优于其他方法。
中图分类号:
[1]LIU S W,DU Q Z,LONG H,et al.Robust Audio WatermarkBased on QR Code[J].Journal of Chinese Computer Systems,2022,43(7):1535-1540. [2]LI X Y,ZHOU X B,LIU Z.High-capacity and robust image wa-termarking algorithm[J].Journal of Jilin University(Enginee-ring and Technology Edition),2022,52(1):174-179. [3]FANG H,ZHANG W,ZHOU H,et al.Screen-shooting resilient watermarking[J].IEEE Transactions on Information Forensics and Security,2018,14(6):1403-1418. [4]ZHU J,KAPLAN R,JOHNSON J,et al.Hidden:Hiding data with deep networks[C]//Proceedings of the European Confe-rence on Computer Vision(ECCV).2018:657-672. [5]JOHNSON N F,JAJODIA S.Exploring steganography:Seeing the unseen[J].Computer,1998,31(2):26-34. [6]SHEISI H,MESGARIAN J,RAHMANI M.Stegano-graphy:Dct coefficient replacement method and compare with JSteg algorithm[J].International Journal of Computer and Electrical Engineering,2012,4(4):458-462. [7]KUNDUR D,HATZINAKOS D.A robust digital image watermarking method using wavelet-based fusion[C]//Proceedings of International Conference on Image Processing.IEEE,1997,1:544-547. [8]FANG H,CHEN D,HUANG Q,et al.Deep template-based watermarking[J].IEEE Transactions on Circuits and Systems for Video Technology,2020,31(4):1436-1451. [9]ZHONG X,HUANG P C,MASTORAKIS S,et al.An automated and robust image watermarking scheme based on deep neural networks[J].IEEE Transactions on Multimedia,2020,23:1951-1961. [10]ZHANG C,BENZ P,KARJAUV A,et al.Udh:Universal deep hiding for steganography,watermarking,and light field messaging[J].Advances in Neural Information Processing Systems,2020,33:10223-10234. [11]TANCIK M,MILDENHALL B,NG R.Stegastamp:Invisiblehyperlinks in physical photo-graphs[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:2117-2126. [12]JIA J,GAO Z,CHEN K,et al.RIHOOP:robust invisible hyperlinks in offline and online photo-graphs[J].IEEE Transactions on Cybernetics,2020:7094-7106. [13]WENGROWSKI E,DANA K.Light field messaging with deep photographic steganography[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:1515-1524. [14]CHENG Y,JI X,WANG L,et al.{mID}:Tracing screen photos via {Moiré} patterns[C]//30th USENIX Security Symposium(USENIX Security 21).2021:2969-2986. [15]GUGELMANN D,SOMMER D,LENDERS V,et al.Screen watermarking for data theft investigation and attribution[C]//2018 10th International Conference on Cyber Conflict(CyCon).IEEE,2018:391-408. [16]FANG H,CHEN D,WANG F,et al.TERA:Screen-to-Camera Image Code with Transparency,Efficiency,Robustness and Adaptability[J].IEEE Transactions on Multimedia,2021,24:955-967. [17]RONNEBERGER O,FISCHER P,BROX T.Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention.2015:234-241. [18]ZHANG R,ISOLA P,EFROS A A,et al.The unreason-able effectiveness of deep features as aperceptual metric[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:586-595. [19]HUISKES M J,LEW M S.The mir flickr retrieval evaluation[C]//Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval.2008:39-43. [20]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014. |
|