基于transformer和自适应嵌入策略的可逆信息隐藏

周琳娜; 陆智高; 尤玮珂; 房笑妃

doi:10.1631/FITEE.2300041

Your Location：

Home >

Browse articles >

基于transformer和自适应嵌入策略的可逆信息隐藏

常规文章 | Updated：2023-08-29

- 基于transformer和自适应嵌入策略的可逆信息隐藏
  Enhanced Publication
- Reversible data hiding using a transformer predictor and an adaptive embedding strategy
- 信息与电子工程前沿（英文） 2023年24卷第8期页码：1143-1155
- Affiliations：
  
  1.School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100084, China
  2.School of Information Science & Technology, University of International Relations, Beijing 100091, China
- Author bio：
  
  †E-mail: zhoulinna@bupt.edu.cn
  luchen@uir.edu.cn
  ‡Corresponding author
- Funds：
  
  National Natural Science Foundation of China(62172053);National Key Research and Development Program of China(2021YFC3340701;2021YFC3340602)
- DOI：10.1631/FITEE.2300041
  中图分类号： TP309
- 纸质出版日期：2023-08-0 ，
  
  收稿日期：2023-01-20，
  
  录用日期：2023-02-28
- Accepted：
Scan QR Code
周琳娜, 陆智高, 尤玮珂, 等. 基于transformer和自适应嵌入策略的可逆信息隐藏[J]. 信息与电子工程前沿（英文）, 2023,24(8):1143-1155.

LINNA ZHOU, ZHIGAO LU, WEIKE YOU, et al. Reversible data hiding using a transformer predictor and an adaptive embedding strategy. [J]. Frontiers of information technology & electronic engineering, 2023, 24(8): 1143-1155.
周琳娜, 陆智高, 尤玮珂, 等. 基于transformer和自适应嵌入策略的可逆信息隐藏[J]. 信息与电子工程前沿（英文）, 2023,24(8):1143-1155. DOI： 10.1631/FITEE.2300041.

LINNA ZHOU, ZHIGAO LU, WEIKE YOU, et al. Reversible data hiding using a transformer predictor and an adaptive embedding strategy. [J]. Frontiers of information technology & electronic engineering, 2023, 24(8): 1143-1155. DOI： 10.1631/FITEE.2300041.

摘要

在可逆信息隐藏（RDH）领域中，设计高精度预测器以减少嵌入失真和开发有效的嵌入策略以最小化由嵌入信息引起的失真是提高RDH性能的两个关键方面。本文提出一种新的RDH方法，包括基于transformer的预测器和具有多个嵌入规则的新嵌入策略。在预测器部分，我们首先设计了一个基于transformer的预测器。然后，提出一种图像分割方法，将图像分成4部分，可以使用更多的像素作为上下文。与其他预测器相比，我们的预测器可以将用于预测的像素范围从相邻像素扩展到全局像素，从而使其在减少嵌入失真方面更为准确。在嵌入策略部分，我们首先提出了能够利用目标块中像素的复杂性度量。然后，开发了一种改进的预测误差排序规则。最后，我们首次提出一种包含多个嵌入规则的嵌入策略。本文中的RDH方法可以有效减少失真，同时在提高隐藏图像的视觉质量方面提供令人满意的结果。实验结果表明，本文中提出的RDH算法的性能处于领先地位。

Abstract

In the field of reversible data hiding (RDH)

designing a high-precision predictor to reduce the embedding distortion and developing an effective embedding strategy to minimize the distortion caused by embedding information are the two most critical aspects. In this paper

we propose a new RDH method

including a predictor based on a transformer and a novel embedding strategy with multiple embedding rules. In the predictor part

we first design a transformer-based predictor. Then

we propose an image division method to divide the image into four parts

which can use more pixels as context. Compared with other predictors

the transformer-based predictor can extend the range of pixels for prediction from neighboring pixels to global ones

making it more accurate in reducing the embedding distortion. In the embedding strategy part

we first propose a complexity measurement with pixels in the target blocks. Then

we develop an improved prediction error ordering rule. Finally

we provide an embedding strategy including multiple embedding rules for the first time. The proposed RDH method can effectively reduce the distortion and provide satisfactory results in improving the visual quality of data-hidden images

and experimental results show that the performance of our RDH method is leading the field.

关键词

可逆信息隐藏Transformer自适应嵌入策略

Keywords

Reversible data hidingTransformerAdaptive embedding strategy

references

Chen M, Chen ZY, Zeng X, et al., 2010. Model order selection in reversible image watermarking. IEEE J Sel Top Signal Process, 4(3):592-604. doi: 10.1109/JSTSP.2010.2049222http://doi.org/10.1109/JSTSP.2010.2049222

Chen M, Radford A, Child R, et al., 2020. Generative pretraining from pixels. Proc 37th Int Conf on Machine Learning, Article 158.

Coltuc D, 2011. Improved embedding for prediction-based reversible watermarking. IEEE Trans Inform Forens Secur, 6(3):873-882. doi: 10.1109/TIFS.2011.2145372http://doi.org/10.1109/TIFS.2011.2145372

Coltuc D, 2012. Low distortion transform for reversible watermarking. IEEE Trans Image Process, 21(1):412-417. doi: 10.1109/TIP.2011.2162424http://doi.org/10.1109/TIP.2011.2162424

Cox IJ, Miller ML, Bloom JA, 2002. Digital Watermarking. Morgan Kaufmann, San Francisco, USA.

Dosovitskiy A, Beyer L, Kolesnikov A, et al., 2021. An image is worth 16×16 words: transformers for image recognition at scale. Proc Int Conf on Learning Representations.

Dragoi IC, Caciula I, Coltuc D, 2018. Improved pairwise pixel-value-ordering for high-fidelity reversible data hiding. Proc 25th IEEE Int Conf on Image Processing, p.1668-1672. doi: 10.1109/ICIP.2018.8451299http://doi.org/10.1109/ICIP.2018.8451299

Esser P, Rombach R, Ommer B, 2021. Taming transformers for high-resolution image synthesis. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.12873-12883. doi: 10.1109/CVPR46437.2021.01268http://doi.org/10.1109/CVPR46437.2021.01268

Goodfellow I, Pouget-Abadie J, Mirza M, et al., 2014. Generative adversarial nets. Proc 27th Int Conf on Neural Information Processing Systems, p.2672-2680.

He WG, Cai ZC, 2021. Reversible data hiding based on dual pairwise prediction-error expansion. IEEE Trans Image Process, 30:5045-5055. doi: 10.1109/TIP.2021.3078088http://doi.org/10.1109/TIP.2021.3078088

He WG, Cai J, Zhou K, et al., 2017. Efficient PVO-based reversible data hiding using multistage blocking and prediction accuracy matrix. J Vis Commun Image Represent, 46:58-69. doi: 10.1016/j.jvcir.2017.03.010http://doi.org/10.1016/j.jvcir.2017.03.010

Hong W, 2012. Adaptive reversible data hiding method based on error energy control and histogram shifting. Opt Commun, 285(2):101-108. doi: 10.1016/j.optcom.2011.09.005http://doi.org/10.1016/j.optcom.2011.09.005

Howard PG, Vitter JS, 2016. Arithmetic coding for data compression. In: Kao MY (Ed.), Encyclopedia of Algorithms. Springer, New York, USA, p.145-150. doi: 10.1007/978-1-4939-2864-4_34http://doi.org/10.1007/978-1-4939-2864-4_34

Hu RW, Xiang SJ, 2021. CNN prediction based reversible data hiding. IEEE Signal Process Lett, 28:464-468. doi: 10.1109/LSP.2021.3059202http://doi.org/10.1109/LSP.2021.3059202

Hu RW, Xiang SJ, 2022. Reversible data hiding by using CNN prediction and adaptive embedding. IEEE Trans Patt Anal Mach Intell, 44(12):10196-10208. doi: 10.1109/TPAMI.2021.3131250http://doi.org/10.1109/TPAMI.2021.3131250

Jafar IF, Darabkh KA, Al-Zubi RT, et al., 2016. Efficient reversible data hiding using multiple predictors. Comput J, 59(3):423-438. doi: 10.1093/comjnl/bxv067http://doi.org/10.1093/comjnl/bxv067

Karras T, Aila T, Laine S, et al., 2018. Progressive growing of GANs for improved quality, stability, and variation. Proc 6th Int Conf on Learning Representations.

Karras T, Laine S, Aila T, 2019. A style-based generator architecture for generative adversarial networks. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.4401-4410. doi: 10.1109/CVPR.2019.00453http://doi.org/10.1109/CVPR.2019.00453

Li XL, Yang B, Zeng TY, 2011. Efficient reversible water- marking based on adaptive prediction error expansion and pixel selection. IEEE Trans Image Process, 20(12):3524-3533. doi: 10.1109/TIP.2011.2150233http://doi.org/10.1109/TIP.2011.2150233

Li XL, Li J, Li B, et al., 2013. High-fidelity reversible data hiding scheme based on pixel-value-ordering and prediction error expansion. Signal Process, 93(1):198-205. doi: 10.1016/j.sigpro.2012.07.025http://doi.org/10.1016/j.sigpro.2012.07.025

Liu ZW, Luo P, Wang XG, et al., 2015. Deep learning face attributes in the wild. Proc IEEE Int Conf on Computer Vision, p.3730-3738. doi: 10.1109/ICCV.2015.425http://doi.org/10.1109/ICCV.2015.425

Luo LX, Chen ZY, Chen M, et al., 2010. Reversible image watermarking using interpolation technique. IEEE Trans Inform Forens Secur, 5(1):187-193. doi: 10.1109/TIFS.2009.2035975http://doi.org/10.1109/TIFS.2009.2035975

Ou B, Li XL, Zhao Y, et al., 2013. Pairwise prediction error expansion for efficient reversible data hiding. IEEE Trans Image Process, 22(12):5010-5021. doi: 10.1109/TIP.2013.2281422http://doi.org/10.1109/TIP.2013.2281422

Ou B, Li XL, Zhao Y, et al., 2014. Reversible data hiding using invariant pixel-value-ordering and prediction error expansion. Signal Process Image Commun, 29(7):760-772. doi: 10.1016/j.image.2014.05.003http://doi.org/10.1016/j.image.2014.05.003

Ou B, Li XL, Wang JW, 2016. High-fidelity reversible data hiding based on pixel-value-ordering and pairwise prediction error expansion. J Vis Commun Image Represent, 39:12-23. doi: 10.1016/j.jvcir.2016.05.005http://doi.org/10.1016/j.jvcir.2016.05.005

Peng F, Li XL, Yang B, 2014. Improved PVO-based reversible data hiding. Dig Signal Process, 25:255-265. doi: 10.1016/j.dsp.2013.11.002http://doi.org/10.1016/j.dsp.2013.11.002

Qu XC, Kim HJ, 2015. Pixel-based pixel value ordering predictor for high-fidelity reversible data hiding. Signal Process, 111:249-260. doi: 10.1016/j.sigpro.2015.01.002http://doi.org/10.1016/j.sigpro.2015.01.002

Russakovsky O, Deng J, Su H, et al., 2015. ImageNet large scale visual recognition challenge. Int J Comput Vis, 115(3):211-252. doi: 10.1007/s11263-015-0816-yhttp://doi.org/10.1007/s11263-015-0816-y

Sachnev V, Kim HJ, Nam J, et al., 2009. Reversible watermarking algorithm using sorting and prediction. IEEE Trans Circ Syst Video Technol, 19(7):989-999. doi: 10.1109/TCSVT.2009.2020257http://doi.org/10.1109/TCSVT.2009.2020257

Thodi DM, Rodriguez JJ, 2007. Expansion embedding techniques for reversible watermarking. IEEE Trans Image Process, 16(3):721-730. doi: 10.1109/TIP.2006.891046http://doi.org/10.1109/TIP.2006.891046

Tian J, 2003. Reversible data embedding using a difference expansion. IEEE Trans Circ Syst Video Technol, 13(8):890-896. doi: 10.1109/TCSVT.2003.815962http://doi.org/10.1109/TCSVT.2003.815962

van den Oord A, Vinyals O, Kavukcuoglu K, 2017. Neural discrete representation learning. Proc 31st Int Conf on Neural Information Processing Systems, p.6309-6318.

Vaswani A, Shazeer N, Parmar N, et al., 2017. Attention is all you need. Proc 31st Int Conf on Neural Information Processing Systems, p.6000-6010.

Wang X, Ding J, Pei QQ, 2015. A novel reversible image data hiding scheme based on pixel value ordering and dynamic pixel block partition. Inform Sci, 310:16-35. doi: 10.1016/j.ins.2015.03.022http://doi.org/10.1016/j.ins.2015.03.022

Wang XY, Wang XY, Ma B, et al., 2021. High precision error prediction algorithm based on ridge regression predictor for reversible data hiding. IEEE Signal Process Lett, 28:1125-1129. doi: 10.1109/LSP.2021.3080181http://doi.org/10.1109/LSP.2021.3080181

Weng SW, Zhang GH, Pan JS, et al., 2017. Optimal PPVO-based reversible data hiding. J Vis Commun Image Represent, 48:317-328. doi: 10.1016/j.jvcir.2017.05.005http://doi.org/10.1016/j.jvcir.2017.05.005

Weng SW, Shi YQ, Hong W, et al., 2019. Dynamic improved pixel value ordering reversible data hiding. Inform Sci, 489:136-154. doi: 10.1016/j.ins.2019.03.032http://doi.org/10.1016/j.ins.2019.03.032

Zhang T, Li XL, Qi WF, et al., 2020a. Location-based PVO and adaptive pairwise modification for efficient reversible data hiding. IEEE Trans Inform Forens Secur, 15:2306-2319. doi: 10.1109/TIFS.2019.2963766http://doi.org/10.1109/TIFS.2019.2963766

Zhang T, Li XL, Qi WF, et al., 2020b. Prediction error value ordering for high-fidelity reversible data hiding. Proc 26th Int Conf on Multimedia Modeling, p.317-328. doi: 10.1007/978-3-030-37731-1_26http://doi.org/10.1007/978-3-030-37731-1_26

Zheng CX, Cham TJ, Cai JF, et al., 2022. Bridging global context interactions for high-fidelity image completion. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.11512-11522. doi: 10.1109/CVPR52688.2022.01122http://doi.org/10.1109/CVPR52688.2022.01122

Zhou BL, Lapedriza A, Khosla A, et al., 2018. Places: a 10 million image database for scene recognition. IEEE Trans Patt Anal Mach Intell, 40(6):1452-1464. doi: 10.1109/TPAMI.2017.2723009http://doi.org/10.1109/TPAMI.2017.2723009

浏览量

174

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Reversible data hiding scheme for encrypted JPEG bitstreams using adaptive RZL rotation

Transformer in reinforcement learning for decision-making: a survey

A robust tensor watermarking algorithm for diffusion-tensor images

Style-conditioned music generation with Transformer-GANs

VG-DOCoT: a novel DO-Conv and transformer framework via VAE-GAN technique for EEG emotion recognition