浏览全部资源
扫码关注微信
Published： 16 February 2024 ，
移动端阅览
贾孟霖， 杨杨， 孙冬. 2024. 具有超分辨率行为伪装效果的可逆图像隐藏. 中国图象图形学报， 29(02):0382-0394
Jia Menglin， Yang Yang， Sun Dong. 2024. Reversible image hiding with super-resolution behavior camouflage effect. Journal of Image and Graphics， 29(02):0382-0394
目的
2
图像隐藏已成为计算机视觉领域的一个重要课题，其目的是以难以察觉的方式将秘密图像隐藏在载体图像中，同时要求接收端能够恢复秘密图像。尽管该技术发展迅速，但目前的图像隐藏技术大多是从内容层面进行伪装，追求载密图像与载体图像的不可区分性。其实，图像隐藏的本质是对行为安全的追求，因此不仅可以在内容层面进行伪装，还可以在行为层面进行伪装。
方法
2
本文从行为安全的角度出发，提出了一种基于超分辨率行为伪装的可逆图像隐藏方法。与传统的图像隐藏技术不同，本文首先将秘密图像可逆地隐藏到载体图像中，生成载密图像，然后通过可逆的超分辨率处理创建与普通超分辨率图像处理操作无法区分的伪装图像。最后，允许接收方从伪装图像中恢复秘密图像和载体图像。
结果
2
在图像隐藏和超分辨率两个任务中，本文方法均取得了优异的结果。在相同的数据集下，测试结果显示恢复秘密图像的峰值信噪比（peak signal-to-noise ratio， PSNR）值达到47+ dB，较对比方法提升了2%以上，结构相似度（structure similarity index measure， SSIM）值也达到0.99+，超分辨率图像与Bicubic、SRCNN（super-resolution convolutional neural network）方法的结果相比，峰值信噪比（PSNR）提升了2+ dB， 感知指数（perceptual index， PI）值降低了2.02+。
结论
2
本文提出的图像隐藏框架利用可逆超分辨率处理操作实现了行为安全角度的图像隐藏，在容量、安全性和精度上都具有优势。
Objective
2
Image hiding has recently become a hotspot in the computer vision field. It aims to hide the secret image in a cover image imperceptibly and recover the secret image， preferably at the receiver. Traditional image hiding methods often adjust the cover image’s pixel value in the spatial domain or modify the cover image’s frequency coefficients to hide the secret information. These methods hide secret images through handcrafted feature information. Thus， these secret images can be detected easily by existing detection techniques. These methods have weak security and lack significant capabilities for hiding information in images. Therefore， they fall short of meeting the demands of large-capacity image hiding tasks. Image hiding methods based on deep learning have been quickly developed with the advancements in convolutional neural networks. These deep learning methods seek to achieve a high level of capacity， invisibility， and recovery accuracy. However， the existing image hiding techniques can be easily detected by deep learning analysis methods because of the rapid development of steganalysis. Handcrafted image hiding methods and image hiding methods based on deep learning are camouflaged from the content level to pursue the indistinguishability of the marked image and the cover image. The essence of image hiding is the pursuit of behavioral security； that is， the pursuit of hiding secret information is inseparable from the behavior of normal users to achieve good detection resistance. Therefore， we can camouflage at the content level and disguise at the behavior level. We innovatively use super-resolution， a common image processing technology， as our behavior camouflage means to realize image hiding from the behavior security perspective.
Method
2
In general， traditional image hiding techniques tend to prioritize the indistinguishability of the cover image and the secret image at the content level. However， we aim to achieve image hiding from a behavioral security perspective in our study. In particular， we aim to make steganographic behavior indistinguishable from regular super-resolution image processing behavior. The entire method can be divided into three modules： forward hiding， super-resolution behavior camouflage， and backward revealing. In the first module， a cover image and a secret image are inputted to the forward hiding module， resulting in a marked image that looks identical to the cover image but with hidden information and information that is lost during forward hiding. The second module involves a lightweight super-resolution rescaling network to realize behavior camouflage. Instead of using traditional convolution for upsampling and downsampling， bicubic interpolation is used. Moreover， we use a pretrained Visual Geometry Group-19（VGG19） network to extract high-level features and guide the generation of super-resolution behavior camouflage images. The final module is backward revealing. The marked image is first reconstructed using the reversibility of the behavior camouflage module. Then， the reconstructed image and auxiliary matrix are inputted into the backward revealing module to recover the secret image and the cover image.
Result
2
Experiments are conducted on recovering secret images， camouflage effect of super-resolution behavior， parameter setting， and ablation. Results show that the invisibility， hiding capacity， and recovery accuracy of our method reach a good level. Only the recovery accuracy of our method is slightly lower than that of the current state-of-the-art （SOTA）. In particular， the peak signal-to-noise ratio （PSNR） between the secret image and the recovered secret image using our method can reach 47.23 dB， which is approximately 0.92 dB less than that using SOTA. Moreover， the structural similarity index measure of our method can reach 0.993 8， which is 0.003 4 less than that of SOTA. However， compared with other methods besides SOTA， our method has advantages. Our method’s super-resolution behavior camouflage reaches a satisfactory level. Given the reversibility constraints， we do not look for top-of-the-line super-resolution effects. Our super-resolution behavior camouflage images have a PSNR of 27.43 dB and a perceptual index of 4.568 4， indicating that they reach the satisfaction of human eyes， whether subjectively or objectively. In addition to the above two main indicators， exploratory experiments on the selection of superparameters， module architecture， and loss function are conducted to find the optimal setting and achieve a good combination effect.
Conclusion
2
This study proposes a new idea of image hiding in which the process of hiding the secret image， namely， super-resolution processing， is performed simultaneously to obtain a super-resolution behavioral camouflage image with secret information. Thus， the attention of unauthorized parties is diverted， and the protection of the secret image is realized. The experimental results show that our method can achieve high capacity， high invisibility， and high recovery accuracy and plays a good role in the confusion of unauthorized parties. Finally， camouflage images still maintain good visual effects.
图像隐藏可逆神经网络（INN）行为安全可逆行为伪装超分辨率深度学习
image hidinginvertible neural network（INN）behavior securityreversible behavior camouflagesuper-resolutiondeep learning
Agustsson E and Timofte R. 2017. NTIRE 2017 challenge on single image super-resolution： dataset and study//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops （CVPRW）. Honolulu， USA： IEEE： 1122-1131 ［DOI： 10.1109/CVPRW.2017.150http://dx.doi.org/10.1109/CVPRW.2017.150］
Ardizzone L， Lüth C， Kruse J， Rother C and Köthe U. 2019. Guided image generation with conditional invertible neural network ［EB/OL］. ［2023-07-18］. https://arxiv.org/pdf/1907.02392.pdfhttps://arxiv.org/pdf/1907.02392.pdf
Baluja S. 2017. Hiding images in plain sight： deep steganography//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach， USA： Curran Associates Inc.： 2066-2076.
Baluja S. 2020. Hiding images within images. IEEE Transactions on Pattern Analysis and Machine Intelligence， 42（7）： 1685-1697 ［DOI： 10.1109/TPAMI.2019.2901877http://dx.doi.org/10.1109/TPAMI.2019.2901877］
Blau Y， Mechrez R， Timofte R， Michaeli T and Zelnik-Manor L. 2019. The 2018 PIRM challenge on perceptual image super-resolution//Proceedings of 2019 European Conference on Computer Vision. Munich， Germany： Springer： 334-355 ［DOI： 10.1007/978-3-030-11021-5_21http://dx.doi.org/10.1007/978-3-030-11021-5_21］
Boroumand M， Chen M and Fridrich J. 2019. Deep residual network for steganalysis of digital images. IEEE Transactions on Information Forensics and Security， 14（5）： 1181-1193 ［DOI： 10.1109/TIFS.2018.2871749http://dx.doi.org/10.1109/TIFS.2018.2871749］
Dinh L， Krueger D and Bengio Y. 2014. Nice： non-linear independent components estimation//Proceedings of the 3rd International Conference on Learning Representations. San Diego， USA： ICLR
Dinh L， Sohl-Dickstein J and Bengio S. 2017. Density estimation using Real NVP//Proceedings of the 5th International Conference on Learning Representations. Toulon， France： OpenReview.net
Dong C， Loy C C， He K M and Tang X O. 2016. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence， 38（2）： 295-307 ［DOI： 10.1109/TPAMI.2015.2439281http://dx.doi.org/10.1109/TPAMI.2015.2439281］
Guan Z Y， Jing J P， Deng X， Xu M， Jiang L， Zhang Z and Li Y P. 2023. DeepMIH： deep invertible network for multiple image hiding. IEEE Transactions on Pattern Analysis and Machine Intelligence， 45（1）： 372-390 ［DOI： 10.1109/TPAMI.2022.3141725http://dx.doi.org/10.1109/TPAMI.2022.3141725］
He K M， Zhang X Y， Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas， USA： IEEE： 770-778 ［DOI： 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90］
Holub V and Fridrich J. 2013. Random projections of residuals for digital image steganalysis. IEEE Transactions on Information Forensics and Security， 8（12）： 1996-2006 ［DOI： 10.1109/TIFS.2013.2286682http://dx.doi.org/10.1109/TIFS.2013.2286682］
Hsu C T and Wu J L. 1999. Hidden digital watermarks in images. IEEE Transactions on Image Processing， 8（1）： 58-68 ［DOI： 10.1109/83.736686http://dx.doi.org/10.1109/83.736686］
Hu Y H， Wang Z C and Zhang X P. 2021. Steganography in social networks based on behavioral correlation. IETE Technical Review， 38（1）： 93-99 ［DOI： 10.1080/02564602.2020.1721340http://dx.doi.org/10.1080/02564602.2020.1721340］
Jing J P， Deng X， Xu M， Wang J Y and Guan Z Y. 2021. HiNet： deep image hiding by invertible network//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision. Montreal， Canada： IEEE： 4713-4722 ［DOI： 10.1109/ICCV48922.2021.00469http://dx.doi.org/10.1109/ICCV48922.2021.00469］
Kingma D P and Dhariwal P. 2018. Glow： generative flow with invertible 1×1 convolutions//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal， Canada： Curran Associates Inc
Li S and Zhang X P. 2019. Toward construction-based data hiding： from secrets to fingerprint images. IEEE Transactions on Image Processing， 28（3）： 1482-1497 ［DOI： 10.1109/TIP.2018.2878290http://dx.doi.org/10.1109/TIP.2018.2878290］
Liu Y， Qin Z Y， Anwar S， Ji P， Kim D， Caldwell S and Gedeon T. 2021. Invertible denoising network： a light solution for real noise removal//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville， USA： IEEE： 13360-13369 ［DOI： 10.1109/CVPR46437.2021.01316http://dx.doi.org/10.1109/CVPR46437.2021.01316］
Lu S P， Wang R， Zhong T and Rosin P L. 2021. Large-capacity image steganography based on invertible neural networks//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， USA： IEEE： 10811-10820 ［DOI： 10.1109/CVPR46437.2021.01067http://dx.doi.org/10.1109/CVPR46437.2021.01067］
Mielikainen J. 2006. LSB matching revisited. IEEE Signal Processing Letters， 13（5）： 285-287 ［DOI： 10.1109/LSP.2006.870357http://dx.doi.org/10.1109/LSP.2006.870357］
Mou C， Xu Y M， Song J C， Zhao C， Ghanem B and Zhang J. 2023. Large-capacity and flexible video steganography via invertible neural network//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， Canada： IEEE： 22606-22615
Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition//Proceedings of the 3rd International Conference on Learning Representations. San Diego， USA： ICLR
Tamimi A A， Abdalla A M and Al-Allaf O. 2013. Hiding an image inside another image using variable-rate steganography. International Journal of Advanced Computer Science and Applications， 4（10）： 18-21 ［DOI： 10.14569/IJACSA.2013.041004http://dx.doi.org/10.14569/IJACSA.2013.041004］
Timofte R， Agustsson E， Van Gool L， Yang M H， Zhang L， Lim B， Son S， Kim H， Nah S， Lee K M， Wang X T， Tian Y P， Yu K， Zhang Y L， Wu S X， Dong C， Lin L， Qiao Y， Loy C C， Bae W， Yoo J， Han Y， Ye J C， Choi J S， Kim M， Fan Y C， Yu J H， Han W， Liu D， Yu H C， Wang Z Y， Shi H H， Wang X C， Huang T S， Chen Y J， Zhang K， Zuo W M， Tang Z M， Luo L K， Li S H， Fu M， Cao L， Heng W， Bui G， Le T， Duan Y， Tao D C， Wang R X， Lin X， Pang J X， Xu J C， Zhao Y， Xu X Y， Pan J S， Sun D Q， Zhang Y J， Song X B， Dai Y C， Qin X Y， Huynh X P， Guo T T， Mousavi H S， Vu T H， Monga V， Cruz C， Egiazarian K， Katkovnik V， Mehta R， Jain A K， Agarwalla A， Praveen C V S， Zhou R F， Wen H D， Zhu C， Xia Z Q， Wang Z T and Guo Q. 2017. NTIRE 2017 challenge on single image super-resolution： methods and results//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops （CVPRW）， Honolulu， USA： IEEE： 1110-1121 ［DOI： 10.1109/CVPRW.2017.149http://dx.doi.org/10.1109/CVPRW.2017.149］
Ur Rehman A， Rahim R， Nadeem S and Ul Hussain S. 2018. End-to-end trained CNN encoder-decoder networks for image steganography//Proceedings of 2018 European Conference on Computer Vision. Munich， Germany： Springer： 723-729 ［DOI： 10.1007/978-3-030-11018-5_64http://dx.doi.org/10.1007/978-3-030-11018-5_64］
Wang J， Chen K J， Zhang W M and Yu N H. 2023. Image processing network-inverted identifiable secure natural steganography. Journal of Image and Graphics， 28（3）： 749-759
王健， 陈可江， 张卫明， 俞能海. 2023. 面向可逆图像处理网络的可证安全自然隐写. 中国图象图形学报， 28（3）： 749-759 ［DOI： 10.11834/jig.220529http://dx.doi.org/10.11834/jig.220529］
Wang X T， Yu K， Wu S X， Gu J J， Liu Y H， Dong C， Qiao Y and Loy C C. 2018. ESRGAN： enhanced super-resolution generative adversarial networks//Proceedings of 2018 European Conference on Computer Vision. Munich， Germany： Springer： 63-79 ［DOI： 10.1007/978-3-030-11021-5_5http://dx.doi.org/10.1007/978-3-030-11021-5_5］
Wang Z， Bovik A C， Sheikh H R and Simoncelli E P. 2004. Image quality assessment： from error visibility to structural similarity. IEEE Transactions on Image Processing， 13（4）： 600-612 ［DOI： 10.1109/TIP.2003.819861http://dx.doi.org/10.1109/TIP.2003.819861］
Weng X Y， Li Y Z， Chi L and Mu Y D. 2019. High-capacity convolutional video steganography with temporal residual modeling//Proceedings of 2019 on International Conference on Multimedia Retrieval. Ottawa， Canada： ACM： 87-95［DOI： 10.1145/3323873.3325011http://dx.doi.org/10.1145/3323873.3325011］
Wu H C， Wu N I， Tsai C S and Hwang M S. 2005. Image steganographic scheme based on pixel-value differencing and LSB replacement methods. IEE Proceedings-Vision， Image， and Signal Processing， 152（5）： 611-615 ［DOI： 10.1049/IP-VIS：20059022http://dx.doi.org/10.1049/IP-VIS：20059022］
Xiao M Q， Zheng S X， Liu C， Wang Y L， He D， Ke G L， Bian J， Lin Z C and Liu T Y. 2020. Invertible image rescaling//Proceedings of the 16th European Conference on Computer Vision. Glasgow， UK： Springer： 126-144 ［DOI： 10.1007/978-3-030-58452-8_8http://dx.doi.org/10.1007/978-3-030-58452-8_8］
Xu G S， Wu H Z and Shi Y Q. 2016. Structural design of convolutional neural networks for steganalysis. IEEE Signal Processing Letters， 23（5）： 708-712 ［DOI： 10.1109/LSP.2016.2548421http://dx.doi.org/10.1109/LSP.2016.2548421］
Xu Y and Xia Z H. 2023. Sender-deniable image steganography. Journal of Image and Graphics， 28（3）： 760-774
徐勇， 夏志华. 2023. 发送方可否认图像隐写. 中国图象图形学报， 28（3）： 760-774［DOI： 10.11834/jig.220541http://dx.doi.org/10.11834/jig.220541］
Xu Y M， Mou C， Hu Y J， Xie J F and Zhang J. 2022. Robust invertible image steganography//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）. New Orleans， USA： IEEE： 7865-7874 ［DOI： 10.1109/CVPR52688.2022.00772http://dx.doi.org/10.1109/CVPR52688.2022.00772］
You W K， Zhang H and Zhao X F. 2021. A Siamese CNN for image steganalysis. IEEE Transactions on Information Forensics and Security， 16： 291-306 ［DOI： 10.1109/TIFS.2020.3013204http://dx.doi.org/10.1109/TIFS.2020.3013204］
Zhang R， Zhu F， Liu J Y and Liu G S. 2020. Depth-wise separable convolutions and multi-level pooling for an efficient spatial CNN-based steganalysis. IEEE Transactions on Information Forensics and Security， 15： 1138-1150 ［DOI： 10.1109/TIFS.2019.2936913http://dx.doi.org/10.1109/TIFS.2019.2936913］
Zhang W M， Wang H X， Li B， Ren Y Z， Yang Z L， Chen K J， Li W X， Zhang X P and Yu N H. 2022. Overview of steganography on multimedia. Journal of Image and Graphics， 27（6）： 1918-1943
张卫明， 王宏霞， 李斌， 任延珍， 杨忠良， 陈可江， 李伟祥， 张新鹏， 俞能海. 2022. 多媒体隐写研究进展. 中国图象图形学报， 27（6）： 1918-1943 ［DOI： 10.11834/jig.211272http://dx.doi.org/10.11834/jig.211272］
Zhu J R， Kaplan R， Johnson J and Li F F. 2018. Hidden： hiding data with deep networks//Proceedings of 2018 European Conference on Computer Vision. Munich， Germany： Springer： 682-697 ［DOI： 10.1007/978-3-030-01267-0_40http://dx.doi.org/10.1007/978-3-030-01267-0_40］
相关文章
相关作者
相关机构
京公网安备11010802024621