一种基于跨域对抗适应的图像信息隐藏算法

doi:10.3969/j.issn.1671-1122.2023.01.011

摘要/Abstract

摘要：

图像信息隐藏是保障信息安全的重要手段。随着深度学习的快速发展，各类基于该技术的以图藏图式隐写算法被提出，它们大多在图像质量、隐藏安全性或嵌入容量等方面的均衡性上存在不足。针对该问题，文章提出了一种基于跨域对抗适应的图像信息隐藏算法，首先，设计超分辨率网络，将秘密信息藏入放大和缩小后不变的图像内容中，提高秘密信息的嵌入容量；然后，在编码网络中加入注意力机制，使编码网络能够关注主要特征并抑制冗余特征，提高生成图像的分辨率；最后，在生成器网络中加入域适应损失指导载密图像的生成，模型整体采用生成对抗的方式进行训练，减小载体图像和载密图像之间的跨域差异。实验结果表明，与其他以图藏图隐写算法相比，文章所提算法在保证图像质量的同时，提高了信息隐藏的安全性和嵌入容量。

关键词: 信息隐藏, 生成对抗网络, 域适应, 自注意力机制

Abstract:

Image information hiding is one of the important methods to ensure information security. With the growth of deep learning, numerous deep learning-based image to image steganography models have been presented. Most of them are deficient in terms of image quality, hiding security, or embedding capability balance. So, this paper proposed an image information hiding algorithm based on cross-domain adversarial adaptation to address the above problems. First, a super-resolution network was built to embed the secret information into the image content unaffected by zooming in and out, to increase the secret information’s embedding capability. Then, an attention mechanism was introduced to the encoding network to enable the network to focus on the primary features and suppress superfluous features, so enhancing the image’s resolution. Finally, a domain adaption loss was introduced to the generator network to guide the production of the stego image, and the model was trained in a generative adversarial way to reduce the cross-domain difference between the carrier image and the stego image. The experimental results demonstrate that, compared to other steganography techniques, the proposed algorithm improves the security and embedding capability of information hiding while maintaining image quality.

Key words: information hiding, generating adversarial network, domain adaptation, self-attention mechanism

中图分类号:

TP309

李季瑀, 付章杰, 张玉斌. 一种基于跨域对抗适应的图像信息隐藏算法[J]. 信息网络安全, 2023, 23(1): 93-102.

LI Jiyu, FU Zhangjie, ZHANG Yubin. An Image Information Hiding Algorithm Based on Cross-Domain Adversarial Adaptation[J]. Netinfo Security, 2023, 23(1): 93-102.

图/表 9

图1

图2

图3

图4

图5

表1

图6

图7

图8

参考文献 33

[1]	YU Kunliang, CHEN Liquan, WANG Yu, et al. A Channel Coding Information Hiding Algorithm for Images Based on Uniform Cyclic Shift[J]. Multimedia Tools and Applications, 2022, 81(8): 11279-11300. doi: 10.1007/s11042-022-12034-8 URL
[2]	LIN C C, CHANG C C, KAO W J, et al. Efficient Electronic Patient Information Hiding Scheme with Tamper Detection Function for Medical Images[J]. IEEE Access, 2022(10): 18470-18485.
[3]	PAN Feng, LI Jun, YANG Xiaoyuan. Image Steganography Method Based on PVD and Modulus Function[C]// IEEE. 2011 International Conference on Electronics, Communications and Control (ICECC). New York: IEEE, 2011: 282-284.
[4]	MIELIKAINEN J. LSB Matching Revisited[J]. IEEE Signal Processing Letters, 2006, 13(5): 285-287. doi: 10.1109/LSP.2006.870357 URL
[5]	COX I J, MILLER M L, BLOOM J A, et al. Digital Watermarking and Steganography[J]. Morgan Kaufmann, 2008, 11: 61-103.
[6]	FILLER T, JUDAS J, FRIDRICH J. Minimizing Additive Distortion in Steganography Using Syndrome-Trellis Codes[J]. IEEE Transactions on Information Forensics and Security, 2011, 6(3): 920-935. doi: 10.1109/TIFS.2011.2134094 URL
[7]	VOLKHONSKIY D, BORISENKO B, BURNAEV E. Generative Adversarial Networks for Image Steganography[EB/OL]. (2016-11-05)[2022-09-10]. https://openreview.net/pdf?id=H1hoFU9xe.htm.
[8]	TANG Weixuan, LI Bin, TAN Shuquan, et al. CNN-based adversarial embedding for image steganography[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(8): 2074-2087. doi: 10.1109/TIFS.2019.2891237 URL
[9]	SHI Haichao, DONG Jing, WANG Wei, et al. Ssgan: Secure Steganography Based on Generative Adversarial Networks[C]// Springer. In Pacific Rim Conference on Multimedia. Berlin: Springer, 2017: 534-544.
[10]	NGUYEN B C, YOON S M, LEE H-K. Multi Bit Plane Image Steganography[C]// Springer. International Workshop on Digital Watermarking. Berlin:Springer, 2006: 61-70.
[11]	HETAL S, MUTZEL P. A Graph-Theoretic Approach to Steganography[C]// Springer. IFIP International Conference on Communications and Multimedia Security. Berlin:Springer, 2005: 119-128.
[12]	PEVNY T, FILLER T, BAS P. Using High-Dimensional Image Models to Perform Highly Undetectable Steganography[C]// Springer. In International Workshop on Information Hiding. Berlin:Springer, 2010: 161-177.
[13]	HOLUB V, FRIDRICH J. Designing Steganographic Distortion Using Directional Filters[C]// IEEE. 2012 IEEE International Workshop on Information Forensics and Security (WIFS). New York:IEEE, 2012: 234-239.
[14]	HOLUB V, FRIDRICH J, DENEMARK T. Universal Distortion Function for Steganography in an Arbitrary Domain[J]. EURASIP Journal on Information Security, 2014(1): 1-13.
[15]	LI Bin, WANG Ming, HUANG Jiwu, et al. A New Cost Function for Spatial Image Steganography[C]// IEEE. 2014 IEEE International Conference on Image Processing (ICIP). New York:IEEE, 2014: 4206-4210.
[16]	PEVNY T, BAS P, FRIDRICH J. Steganalysis by Subtractive Pixel Adjacency Matrix[J]. IEEE Transactions on Information Forensics and Security, 2010, 5(2): 215-224. doi: 10.1109/TIFS.2010.2045842 URL
[17]	GOODFELLOW L J, POUGET-A J, MIRZA M, et al. Generative Adversarial Nets. Advances in Neural Information Processing Systems[C]// ACM. Proceedings of the 27th International Conference on Neural Information Processing Systems. New York: ACM, 2014: 2672-2680.
[18]	RADFORD A, METZ L, CHINTALA S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks[EB/OL]. (2016-01-07)[2022-09-10]. https://arxiv.org/abs/1511.06434.htm.
[19]	LIU Mingming, ZHANG Minqing, LIU Jia, et al. Coverless Information Hiding Based on Generative Adversarial Networks[J]. Journal of Applied Sciences, 2018, 36(2): 371-382.
	刘明明, 张敏情, 刘佳, 等. 基于生成对抗网络的无载体信息隐藏[J]. 应用科学学报, 2018, 36(2): 371-382.
[20]	BI Xinliang, YANG Haibin, YANG Xiaoyuan, et al. Generative Strganography Scheme Based on StarGAN[J]. Netinfo Security, 2020, 20(12): 64-71.
	毕新亮, 杨海滨, 杨晓元, 等. 基于StarGAN的生成式图像隐写方案[J]. 信息网络安全, 2020, 20(12): 64-71.
[21]	LIN Zhouhan, FENG Minwei, SANTOS C N, et al. A Structured Self-Attentive Sentence Embedding[J]. arXiv preprint arXiv, 2017, 3(9): 1-15.
[22]	ZHANG X, KONG X, WANG P, et al. Cover-Source Mismatch in Deep Spatial Steganalysis[C]//Springer. International Workshop on Digital Watermarking. Berlin:Springer, 2019: 71-83.
[23]	DASTGHEIB M B, JAHROMI M F, NEJAD J T. A Low Cost Image Steganalysis by Using Domain Adaptation[J]. International Journal of Information Science and Management (IJISM), 2018, 16(1): 191-201.
[24]	YANG Yong, KONG Xiangwei, WANG Bo, et al. Steganalysis on Internet Images Via Domain Adaptive Classifier[J]. Neurocomputing, 2019, 351: 205-216. doi: 10.1016/j.neucom.2019.04.025
[25]	WANG Yaojie, YANG Xiaoyuan, LIU jia. Cross-Domain Image Steganography Based on GANs[C]// Springer. International Conference on Security with Intelligent Computing and Big-data Services. Berlin:Springer, 2018: 743-755.
[26]	GABRIEL G. NinaSR: Efficient Small and Large ConvNets for Super-Resolution. GitHub repository[EB/OL]. (2021-08-21)[2022-09-10]. https://github.com/Coloquinte/torchSR.
[27]	DUAN Xintao, LIU Nao, GOU Mengxiao, et al. SteganoCNN: Image Steganography with Generalization Ability Based on Convolutional Neural Network[J]. Entropy, 2020, 22(10): 1155. doi: 10.3390/e22101155 URL
[28]	BOROUMAND M, CHEN Mo, FRIDRICH J. Deep Residual Network for Steganalysis of Digital Images[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(5): 1181-1193. doi: 10.1109/TIFS.2018.2871749 URL
[29]	BALUJA S. Hiding Images within Images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(7): 1685-1697. doi: 10.1109/TPAMI.2019.2901877 pmid: 30835212
[30]	ZHU Jiren, KAPLAN R, JOHNSON J, et al. Hidden: Hiding Data with Deep Networks[C]// Springer. European Conference on Computer Vision (ECCV). Berlin: Springer, 2018: 682-697.
[31]	ZHANG Chaoning, 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.
[32]	LU Shaoping, WANG Rong, ZHANG Tao, et al. Large-Capacity Image Steganography Based on Invertible Neural Networks[C]// IEEE. IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2021: 10816-10825.
[33]	HOLUB V, FRIDRICH J. Low-Complexity Features for JPEG Steganalysis Using Undecimated DCT[J]. IEEE Transactions on Information Forensics and Security, 2015, 10(2): 219-228.

	BALUJA	HiDDeN	UDH	INN	本文方法
载体/ 载密 QF=75 QF=85 QF=95	33.27/84.3% 35.40/95.9% 36.41/96.6%	31.21/77.59% 35.183/94.28% 35.87/98.7%	35.791/91.13% 35.935/96.26% 38.33/98.5%	36.82/91.45% 39.01/96.6% 39.13/97%	37.42/94% 37.69/94.32% 37.95/94.7%
秘密/ 提取 QF=75 QF=85 QF=95	30.33/81% 33.465/91.14% 35.89/95.85%	31.53/82.7% 33.98/94% 34.72/94.8%	35.22/90.53% 34.97/92.3% 37.18/96.7%	35.8/92% 38.115/95.8% 39.355/96%	35.958/92.67% 36.115/91.4% 36.45/93.9%