Driven by noise, the generator of the generative adversarial network (GAN) can generate high-quality digital images and provide a new data carrier for hiding information. In this paper, a coverless information hiding model combining orthogonal GAN and Ushape network is proposed on the fact that the orthogonal GAN discriminator can extract feature codes of the generated image. While hiding information, the binary sequence of the information to be hidden is mapped into a noise vector according to a group quantization rule, and the generator of the orthogonal GAN is driven by the noise vector to generate a hidden digital image. While extracting information, the feature code of the hidden image is extracted by the discriminator of the orthogonal GAN, and then the U-shape network is used to realize the mapping from the feature code to the driving noise, thereby recovering the secret information. By performing adversarial training of the built-in model with the CelebA dataset, the generator can generate high-quality hidden images and the discriminator can be combined with the U-shaped network to extract secret information from the hidden image. Compared with the latest similar algorithms, the proposed model performs better information extraction accuracy and security under the same information hiding capacity with reduced the training overhead and improved practicability.
ZHU Yiming, CHEN Fan, HE Hongjie, CHEN Hongyou
. Orthogonal GAN Information Hiding Model Based on Secret Information Driven[J]. Journal of Applied Sciences, 2019
, 37(5)
: 721
-732
.
DOI: 10.3969/j.issn.0255-8297.2019.05.013
[1] 常卫东, 刘完芳, 童宇. 信息隐藏技术综述[J]. 中国科技信息,2010(3):117-118. Chang W D, Liu W F, Tong Y. A survey of infomation hiding[J]. China Science and Technology Information, 2010(3):117-118. (in Chinese)
[2] Tirkel A Z, Rankin G A, Schyndel R V. Electronic watermark[C]//Digital Image Computing, Technology and Applications, 1993:666-673.
[3] Holub V, Fridrich J, Denemark T. Universal distortion function for steganography in an arbitrary domain[J]. Eurasip Journal on Information Security, 2014, 2014(1):1-13.
[4] Pevný T, Filler T, Bas P. Using high-dimensional image models to perform highly undetectable steganography[J]. Lecture Notes in Computer Science, 2010, 6387:161-177.
[5] Holub V, Fridrich J. Designing steganographic distortion using directional filters[C]//IEEE International Workshop on Information Forensics and Security. IEEE, 2013:234-239.
[6] Lin W H, Horng S J, Kao T W. An efficient watermarking method based on significant difference of wavelet coefficient quantization[J]. IEEE Transactions on Multimedia, 2008, 10(5):746-757.
[7] Cox I J, Kilian J, Leighton F T. Secure spread spectrum watermarking for multimedia[J]. IEEE Transactions on Image Processing, 1997, 6(12):1673-1687
[8] 周志立,曹燚,孙星明. 基于图像bag-of-words模型的无载体信息隐藏[J]. 应用科学学报,2016, 34(5):527-536. Zhou Z L, Cao Y, Sun X M. Coverless information hiding based on bag-of-words model of image[J]. Journal of Applied Sciences, 2016, 34(5):527-536. (in Chinese)
[9] 张新鹏,钱振兴,李晟. 信息隐藏研究展望[J]. 应用科学学报,2016, 34(5):475-489. Zhang X P, Qian Z X, Li S. Prospect of digital steganography research[J]. Journal of Applied Sciences, 2016, 34(5):475-489. (in Chinese)
[10] Otori H, Kuriyama S. Texture synthesis for mobile data communications[J]. IEEE Computer Graphics and Applications, 2009, 29(6):74-81.
[11] Wu K C, Wang C M. Steganography using reversible texture synthesis[J]. IEEE Transactions Image Processing, 2015, 24(1):130-139.
[12] Goodfellow I, Pouget A J, Mirz M, et al. Generative adversarial nets[C]//International Conference on Neural Information Processing Systems, 2014:2672-2680.
[13] Liu J, Ke Y, Lei Y, et al. The reincarnation of grille cipher:a generative approach[DB/OL]. 2018[2018-07-12]. arXiv:1804.06514.
[14] 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)
[15] Odena A, Olah C, Shlens J. Conditional image synthesis with auxiliary classifier GANs[DB/OL]. 2016[2016-10-30]. arXiv:1610.09585.
[16] Hu D H, Wang L, Jiang W J, et al. A novel image steganography method via deep generative adversarial networks[J]. IEEE Access, 2018, 6:38303-38314.
[17] Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[DB/OL]. 2015[2015-11-19]. arXiv:1511.06434.
[18] Su J L. O-gan:extremely concise approach for auto-encoding generative adversarial networks[DB/OL]. 2019[2019-06-18]. arXiv:1903.01931.
[19] Arjovsky M, Chintala S, Bottou L. Wasserstein GAN[DB/OL].2017[2017-01-26]. arXiv:1701.07875v3.
[20] Chen X, Duan Y, Houthooft R, et al. InfoGAN:interpretable representation learning by information maximizing generative adversarial nets[C]//Proceedings of International Conference on Neural Information Processing Systems, 2016:2172-2180.
[21] Ioffe S, Szegedy C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of International Conference on Machine Learning, 2015:448-456.
[22] Kingma D P, Ba J. Adam:a method for stochastic optimization[DB/OL]. 2014[2014-12-22]. arXiv:1412.6980.
[23] Lim J H, Ye J C. Geometric gan[DB/OL]. 2017[2017-05-08]. arXiv:1705.02894.
[24] Zhang H, Goodfellow I, Metaxas D, et al. Self-attention generative adversarial networks[DB/OL]. 2018[2018-05-21].arXiv:1805.08318.
[25] Miyato T, Kataoka T, Koyama M, et al. Spectral normalization for generative adversarial networks[DB/OL]. 2018[2018-02-16]. arXiv:1802.05957.
