面向编码伪装的鲁棒无载体图像隐写方法

doi:10.3969/j.issn.0255-8297.2024.03.009

摘要/Abstract

摘要： 传统的图像隐写方法容易受到隐写分析的攻击，无载体图像隐写方法可以从本质上抵抗隐写分析的攻击。然而，现有的无载体图像隐写算法存在鲁棒性低、提取精度有限和不可感知性差等问题，为此提出一种面向编码伪装的鲁棒无载体图像隐写方法。该方案将基于深度的合成隐写方法与传统的聚类相结合，通过感知哈希对编码网络生成的合成图像与相似图像进行匹配，将传输的图像由合成图像替换成真实自然图像以此提高安全性；进一步，利用聚类算法找到与相似图像对应的伪装图像进行传输。以卷积神经网络特征为基准进行聚类，提高了抗几何攻击的能力。实验分析表明，所提方案在隐藏容量、提取精度方面都有较优的表现，且解决了生成式隐写方案存在的图像质量低和鲁棒性差等问题。

关键词: 无载体图像隐写, 卷积神经网络聚类, 感知哈希, 生成网络, 伪装图像

Abstract: Traditional image steganography methods are susceptible to attack by steganalysis tools, whereas coverless image steganography method can essentially resist the attack of steganalyzers. However, most coverless image steganography algorithms suffer from problems such as low robustness, limited extraction accuracy, and poor imperceptibility. Therefore, this paper proposes a robust coverless steganography method for coding camouflage, which combines depth-based synthetic steganography with traditional clustering algorithms. The proposed algorithm matches the synthetic images generated by the coding network with similar images through perceptual hashing, and converts the transmitted images from synthetic images to real natural images to improve security. In addition, clustering algorithm is used to find the camouflage image which is corresponding to the similar image for transmission. The clustering is based on the convolutional neural networks (CNN) feature, which improves the ability to resist geometric attacks. Experimental analysis demonstrates that the proposed scheme achieves higher capacity and extraction accuracy, and solves the problems of low image quality and poor robustness of generative steganography schemes.

Key words: coverless image steganography, convolutional neural networks (CNN) clustering, perceptual hash, generate networks, camouflage image

中图分类号:

TP309

苑紫烨, 邱宝林, 叶妤, 温文, 化定丽, 张玉书. 面向编码伪装的鲁棒无载体图像隐写方法[J]. 应用科学学报, 2024, 42(3): 469-485.

YUAN Ziye, QIU Baolin, YE Yu, WEN Wenying, HUA Dingli, ZHANG Yushu. A Robust Coverless Image Steganography Method for Coding Camouflage[J]. Journal of Applied Sciences, 2024, 42(3): 469-485.

参考文献

[1] 谢艺艺, 张玉书, 赵若宇, 等. 基于CycleGAN的图像隐私保护[J]. 应用科学学报, 2023, 41(2): 228-239. Xie Y Y, Zhang Y S, Zhao R Y, et al. Image privacy protection based on cycle-consistent generative adversarial networks [J]. Journal of Applied Sciences, 2023, 41(2): 228-239.(in Chinese)
[2] Wen W Y, Fan J C, Zhang Y S, et al. APCAS: autonomous privacy control and authentication sharing in social networks [J]. IEEE Transactions on Computational Social Systems, 2023, 10(6): 3169-3180.
[3] Yang C H, Weng C Y, Wang S J, et al. Adaptive data hiding in edge areas of images with spatial LSB domain systems [J]. IEEE Transactions on Information Forensics and Security, 2008, 3(3): 488-497.
[4] Luo W Q, Huang F J, Huang J W. Edge adaptive image steganography based on LSB matching revisited [J]. IEEE Transactions on Information Forensics and Security, 2010, 5(2): 201-214.
[5] Zhang X P, Wang S Z. Steganography using multiple-base notational system and human vision sensitivity [J]. IEEE Signal Processing Letters, 2005, 12(1): 67-70.
[6] Yu M J, Yao H, Qin C, et al. Reversible data hiding in palette images [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(2): 648-660.
[7] Qin X H, Li B, Tan S Q, et al. Gradually enhanced adversarial perturbations on color pixel vectors for image steganography [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(8): 5110-5123.
[8] Huang F J, Huang J W, Shi Y Q. New channel selection rule for JPEG steganography [J]. IEEE Transactions on Information Forensics and Security, 2012, 7(4): 1181-1191.
[9] Li S, Wang Z, Zhang X, et al. Robust image steganography against general down sampling operations with lossless secret recovery [J]. IEEE Transactions on Dependable and Secure Computing, 2024, 21(1): 340-352.
[10] Guan Q X, Liu P, Zhang W M, et al. Double-layered dual-syndrome trellis codes utilizing channel knowledge for robust steganography [J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 501-516.
[11] Li F Y, Zeng Y S, Zhang X P, et al. Ensemble stego selection for enhancing image steganography [J]. IEEE Signal Processing Letters, 2022, 29: 702-706.
[12] Baluja S. Hiding images within images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(7): 1685-1697.
[13] Rehman A U, Rahim R, Nadeem M S, et al. End-to-end trained CNN encoder-decoder networks for image steganography [C]//The European Conference on Computer Vision, 2018: 723-729.
[14] Zhang R, Dong S Q, Liu J Y. Invisible steganography via generative adversarial networks [J]. Multimedia Tools and Applications, 2019, 78(7): 8559-8575.
[15] 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. Liu M M, Zhang M Q, Liu J, et al. Coverless information hiding based on generative adversarial networks [J]. Journal of Applied Sciences, 2018, 36(2): 371-382. (in Chinese)
[16] Liu M, Song T, Luo W, et al. Adversarial steganography embedding via stego generation and selection [J] IEEE Transactions on Dependable and Secure Computing, 2023, 20(3): 2375-2389.
[17] Liu Q, Xiang X Y, Qin J H, et al. Coverless steganography based on image retrieval of DenseNet features and DWT sequence mapping [J]. Knowledge-Based Systems, 2020, 192: 105375-105389.
[18] Zhou Z L, Mu Y, Wu Q M J, et al. Coverless image steganography using partial-duplicate image retrieval [J]. Soft Computing, 2019, 23(13): 4927-4938.
[19] Luo Y J, Qin J H, Xiang X Y, et al. Coverless real-time image information hiding based on image block matching and dense convolutional network [J]. Journal of Real-Time Image Processing, 2020, 17(1): 125-135.
[20] Li S, Zhang X P. Toward construction based data hiding: from secrets to fingerprint images [J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2018, 28(3): 1482-1497.
[21] Zhou Z L, Su Y C, Li J, et al. Secret-to-image reversible transformation for generative steganography [J]. IEEE Transactions on Dependable and Secure Computing, 2023, 20(5): 4118- 4134.
[22] Liu X, Ma Z, Ma J, et al. Image disentanglement autoencoder for steganography without embedding [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 2293-2302.
[23] Zhang X, Peng F, Long M. Robust coverless image steganography based on DCT and LDA topic classification [J]. IEEE Transactions on Multimedia, 2018, 20(12): 3223-3238.
[24] 王亚宁, 吴槟. 面向无载体信息隐藏的映射关系智能搜索方法[J]. 信息安全学报, 2020, 5(3): 48-61. Wang Y N, Wu B. An intelligent search method of mapping relation for coverless information hiding [J]. Journal of Cyber Security, 2020, 5(3): 48-61. (in Chinese)
[25] Luo Y J, Qin J H, Xiang X Y, et al. Coverless image steganography based on multi-object recognition [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(7): 2779-2791.
[26] Chen X Y, Zhang Z T, Qiu A Q, et al. Novel coverless steganography method based on image selection and StarGAN [J]. IEEE Transactions on Network Science and Engineering, 2022, 9(1): 219-230.
[27] Cao Y, Zhou Z L, Wu Q M J, et al. Coverless information hiding based on the generation of anime characters [J]. EURASIP Journal on Image and Video Processing, 2020(1): 1-15.
[28] Arthur D, Vassilvitskii S. K-means: the advantages of careful seeding [C]//Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, 2007: 1027-1035.
[29] Park T, Zhu J Y, Wang O, et al. Swapping autoencoder for deep image manipulation [C]//Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020: 7198-7211.
[30] Yu F, Seff A, Zhang Y D, et al. LSUN: construction of a large-scale image dataset using deep learning with humans in the Loop [DB/OL]. 2015[2023-11-27]. http://arxiv.org/abs/1506.03365.
[31] Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 4396-4405.
[32] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84-90.
[33] Jegou H, Douze M, Schmid C. Hamming embedding and weak geometric consistency for large scale image search [C]//European Conference on Computer Vision, 2008: 304-317.
[34] Zhu J R, Kaplan R, Johnson J, et al. Hidden: hiding data with deep networks [C]//European Conference on Computer Vision, 2018: 682-697.
[35] Zhang Z, Fu G, Ni R, et al. A generative method for steganography by cover synthesis with auxiliary semantics [J]. Tsinghua Science and Technology, 2020, 25(4): 516-527.
[36] Hu D H, Wang L, Jiang W J, et al. A novel image steganography method via deep convolutional generative adversarial networks [J]. IEEE Access, 2018, 6: 38303-38314.
[37] Li J, Niu K, Liao L, et al. A generative steganography method based on WGAN-GP [C]//The 6th International Conference: Artificial Intelligence and Security (ICAIS 2020), 2020: 386-397.
[38] Yu C, Hu D H, Zheng S L, et al. An improved steganography without embedding based on attention GAN [J]. Peer-to-Peer Networking and Applications, 2021, 14(3): 1446-1457.
[39] Karras T, Laine S, Aittala M, et al. Analyzing and improving the image quality of styleGAN [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 8110-8119.
[40] Zheng S L, Wang L, Ling B, et al. Coverless information hiding based on robust image hashing [C]//The 13th International Conference: Intelligent Computing Methodologies, 2017, 2017: 536-547.
[41] 刘钊志, 赵琰. 一种图像块旋转的马赛克拼图伪装隐写[J]. 应用科学学报, 2023, 41(2): 311-325. Liu Z Z, Zhao Y. A mosaic puzzle camouflage steganography with image block rotation [J]. Journal of Applied Sciences, 2023, 41(2): 311-325. (in Chinese)
[42] Karim N A, Ali S A, Jawad M J. A coverless image steganography based on robust image wavelet hashing [J]. Telecommunication Computing Electronics and Control, 2022, 20(6): 1317- 1325.
[43] Meng L J, Jiang X H, Zhang Z Z, et al. A robust coverless image steganography based on an end-to-end hash generation model [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(7): 3542-3558.