|
|
基于编码–解码网络图像信息隐藏算法
|
Abstract:
传统的图像隐写往往倾向于将隐藏信息安全地嵌入到封面图像中，而几乎忽略了有效负载容量。为解决传统隐写容量低的问题，本文采用深度学习与图像信息隐藏相结合的方法。实验结果表明，在嵌入容量上，所提算法达到了24 bpp，是目前容量最大的图像隐写算法之一。在此大容量嵌入的前提下，所提算法生成的载密图像和提取的秘密图像，无论在主观视觉质量还是客观视觉指标峰值信噪比(PSNR)上都高于其他同类算法，说明了设计的端到端隐写网络的整体优越性。
Traditional image steganography methods often focus on securely embedding hidden information into cover images, while paying little attention to the payload capacity. To address the issue of low embedding capacity in conventional steganography, this paper combines deep learning with image information hiding techniques. Experimental results show that the proposed algorithm achieves an embedding capacity of 24 bpp, making it one of the highest-capacity image steganography algorithms to date. Despite the large embedding capacity, the stego-images generated by the algorithm and the extracted secret images outperform other similar algorithms in both subjective visual quality and objective visual metrics such as Peak Signal-to-Noise Ratio (PSNR). This demonstrates the overall superiority of the designed end-to-end steganography network.
| [1] | Xian, Y., Wang, X., Zhang, Y., Wang, X. and Du, X. (2021) Fractal Sorting Vector-Based Least Significant Bit Chaotic Permutation for Image Encryption. Chinese Physics B, 30, Article ID: 060508. https://doi.org/10.1088/1674-1056/abda35 |
| [2] | Duan, X., Jia, K., Li, B., Guo, D., Zhang, E. and Qin, C. (2019) Reversible Image Steganography Scheme Based on a U-Net Structure. IEEE Access, 7, 9314-9323. https://doi.org/10.1109/access.2019.2891247 |
| [3] | Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W. and Frangi, A., Eds., Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer International Publishing, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28 |
| [4] | Zhang, R., Dong, S. and Liu, J. (2018) Invisible Steganography via Generative Adversarial Networks. Multimedia Tools and Applications, 78, 8559-8575. https://doi.org/10.1007/s11042-018-6951-z |
| [5] | Hayes, J. and Danezis, G. (2017) Generating Steganographic Images via Adversarial Training. Proceedings of the 31st Annual Conference on Neural Information Processing Systems, La Jolla, 1955-1964. |
| [6] | Hu, D., Wang, L., Jiang, W., Zheng, S. and Li, B. (2018) A Novel Image Steganography Method via Deep Convolutional Generative Adversarial Networks. IEEE Access, 6, 38303-38314. https://doi.org/10.1109/access.2018.2852771 |
| [7] | Agustsson, E. and Timofte, R. (2017) NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, 21-26 July 2017, 1122-1131. https://doi.org/10.1109/cvprw.2017.150 |
| [8] | Ardizzone, L., Kruse, J., Rother, C. and Kothe, U. (2018) Analyzing Inverse Problems with Invertible Neural Networks. arXiv: 1808.04730. |
| [9] | Baluja, S. (2017) Hiding Images in Plain Sight: Deep Steganography. In: Guyon, I., Von Luxburg, U., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S. and Garnett, R., Eds., Advances in Neural Information Processing Systems 30, (NeurIPS). |
| [10] | Baluja, S. (2019) Hiding Images within Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 1685-1697. |
| [11] | Dinh, L., Sohl-Dickstein, J. and Bengio, S. (2016) Density Estimation Using Real NVP. arXiv: 1605.08803. |
| [12] | Gilbert, A., Zhang, Y., Lee, K., Zhang, Y. and Lee, H. (2017) Towards Understanding the Invertibility of Convolutional Neural Networks. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, 19-25 August 2017, 1703-1710. https://doi.org/10.24963/ijcai.2017/236 |
| [13] | Baluja, S. (2017) Hiding Images in Plain Sight: Deep Steganography. In: Guyon, I., Von Luxburg, U., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S. and Garnett, R., Eds., Advances in Neural Information Processing Systems 30, (NeurIPS). |
| [14] | He, J.W., Dong, C. and Qiao, Y. (2020) Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration. arXiv: 1912.05293. |
| [15] | Hetzl, S. and Mutzel, P. (2005) A Graph-Theoretic Approach to Steganography. In: Dittmann, J., Katzenbeisser, S. AND Uhl, A., Eds., Communications and Multimedia Security, Springer Berlin Heidelberg, 119-128. https://doi.org/10.1007/11552055_12 |
| [16] | Zhu, J., Kaplan, R., Johnson, J. and Fei-Fei, L. (2018) HiDDeN: Hiding Data with Deep Networks. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer Vision—ECCV 2018, Springer International Publishing, 682-697. https://doi.org/10.1007/978-3-030-01267-0_40 |
| [17] | Ho, J., Chen, X., Srinivas, A., et al. (2019) Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design. International Conference on Machine Learning (ICML), 3. |
| [18] | Huang, C.W., Krueger, D., Lacoste, A. and Courville, A. (2018) Neural Autoregressive Flows. arXiv: 1804.00779. |
