基于深度学习的密钥控制多图隐写技术研究
Deep Learning-Based Key-Controlled Multi-Image Steganography
DOI: 10.12677/mos.2025.144368, PDF,   
作者: 朱嘉伟, 建一飞：上海理工大学光电信息与计算机工程学院，上海
关键词: 图片隐写；密钥；可逆神经网络；多图；Image Steganography； Secret Key； Reversible Neural Network； Multi-Image
摘要: 本研究提出了一种基于可逆神经网络的密钥控制的多图像隐写方案(SDRNN)，以提升安全性和视觉质量。采用私钥加密确保信息安全性，即便算法公开也能保护秘密信息，增强抗攻击能力。针对高容量隐写常见的视觉伪影问题，设计了SCDense模块，通过选择性通道密集连接优化信息嵌入，有效减少轮廓阴影和颜色失真。实验结果表明，相比现有方法，本方案在峰值信噪比(PSNR)和结构相似性(SSIM)等指标上有显著提升，提高了隐写图像的质量和鲁棒性。这显示了该方法不仅理论上有价值，在实际应用中也更可靠、适应性更强。
Abstract: This study proposes a deep learning-enabled, key-controlled multi-image steganographic framework (SDRNN) to enhance security and visual quality. Private key encryption ensures information security, protecting secret information even with public algorithm disclosure, thereby strengthening attack resistance. Addressing common visual artifacts in high-capacity steganography, we design an SCDense module that optimizes information embedding through selective channel dense connections, effectively reducing contour shadows and color distortion. Experimental results demonstrate significant improvements in peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared to existing methods, enhancing both the quality and robustness of stego-images. This indicates the method’s theoretical value and superior practical reliability/adaptability. The research presents a novel effective solution for multi-image steganography, particularly demonstrating notable advantages in security enhancement and visual quality preservation.
文章引用：朱嘉伟, 建一飞. 基于深度学习的密钥控制多图隐写技术研究[J]. 建模与仿真, 2025, 14(4): 1225-1239. https://doi.org/10.12677/mos.2025.144368

参考文献

[1] Malik, A.S., Boyko, O., Aktar, N. and Young, W.F. (2001) A Comparative Study of MR Imaging Profile of Titanium Pedicle Screws. Acta Radiologica, 42, 291-293. [Google Scholar] [CrossRef] [PubMed]
[2] Fridrich, J., Goljan, M. and Rui Du, (2001) Detecting LSB Steganography in Color, and Gray-Scale Images. IEEE Multimedia, 8, 22-28. [Google Scholar] [CrossRef] 
[3] Lerch-Hostalot, D. and Megías, D. (2016) Unsupervised Steganalysis Based on Artificial Training Sets. Engineering Applications of Artificial Intelligence, 50, 45-59. [Google Scholar] [CrossRef] 
[4] Luo, W., Huang, F. and Huang, J. (2010) Edge Adaptive Image Steganography Based on LSB Matching Revisited. IEEE Transactions on Information Forensics and Security, 5, 201-214. [Google Scholar] [CrossRef] 
[5] Pan, F., Li, J. and Yang, X. (2011) Image Steganography Method Based on PVD and Modulus Function. 2011 International Conference on Electronics, Communications and Control (ICECC), Ningbo, 9-11 September 2011, 282-284. [Google Scholar] [CrossRef] 
[6] Ruanaidh, J.J.K.O., Dowling, W.J. and Boland, F.M. (1996) Phase Watermarking of Digital Images. Proceedings of 3rd IEEE International Conference on Image Processing, Lausanne, 19 September 1996, 239-242. [Google Scholar] [CrossRef] 
[7] Hsu, C.-T. and Wu, J.-L. (1999) Hidden Digital Watermarks in Images. IEEE Transactions on Image Processing, 8, 58-68. [Google Scholar] [CrossRef] [PubMed]
[8] Barni, M., Bartolini, F. and Piva, A. (2001) Improved Wavelet-Based Watermarking through Pixel-Wise Masking. IEEE Transactions on Image Processing, 10, 783-791. [Google Scholar] [CrossRef] [PubMed]
[9] Hayes, J. and Danezis, G. (2017) Generating Steganographic Images via Adversarial Training. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 1951-1960.
[10] Volkhonskiy, D., Borisenko, B. and Burnaev, E. (2016) Generative Adversarial Networks for Image Steganography.
https://openreview.net/pdf?id=H1hoFU9xe
[11] Shi, H., Dong, J., Wang, W., Qian, Y. and Zhang, X. (2017) SSGAN: Secure Steganography Based on Generative Adversarial Networks. Advances in Multimedia Information Processing—PCM 2017, Harbin, 28-29 September 2017, 534-544. [Google Scholar] [CrossRef] 
[12] Tang, W., Tan, S., Li, B. and Huang, J. (2017) Automatic Steganographic Distortion Learning Using a Generative Adversarial Network. IEEE Signal Processing Letters, 24, 1547-1551. [Google Scholar] [CrossRef] 
[13] Zhang, K.A., Cuesta-Infante, A., Xu, L., et al. (2019) SteganoGAN: High Capacity Image Steganography with GANs. arXiv: 1901.03892. [Google Scholar] [CrossRef] 
[14] Zhu, J., Kaplan, R., Johnson, J. and Fei-Fei, L. (2018) HiDDeN: Hiding Data with Deep Networks. Computer Vision—ECCV 2018, Munich, 8-14 September 2018, 682-697. [Google Scholar] [CrossRef] 
[15] Ahmadi, M., Norouzi, A., Karimi, N., Samavi, S. and Emami, A. (2020) ReDMark: Framework for Residual Diffusion Watermarking Based on Deep Networks. Expert Systems with Applications, 146, Article 113157. [Google Scholar] [CrossRef] 
[16] Tancik, M., Mildenhall, B. and Ng, R. (2020) StegaStamp: Invisible Hyperlinks in Physical Photographs. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 2114-2123. [Google Scholar] [CrossRef] 
[17] Luo, X., Zhan, R., Chang, H., Yang, F. and Milanfar, P. (2020) Distortion Agnostic Deep Watermarking. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 13545-13554. [Google Scholar] [CrossRef] 
[18] Baluja, S. (2017) Hiding Images in Plain Sight: Deep Steganography. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 2066-2076.
[19] Weng, X., Li, Y., Chi, L. and Mu, Y. (2019) High-Capacity Convolutional Video Steganography with Temporal Residual Modeling. Proceedings of the 2019 on International Conference on Multimedia Retrieval, Ottawa, 10-13 June 2019, 87-95. [Google Scholar] [CrossRef] 
[20] Wu, P., Yang, Y. and Li, X. (2018) Image-into-Image Steganography Using Deep Convolutional Network. Advances in Multimedia Information Processing—PCM 2018, Hefei, 21-22 September 2018, 792-802. [Google Scholar] [CrossRef] 
[21] Wu, P., Yang, Y. and Li, X. (2018) StegNet: Mega Image Steganography Capacity with Deep Convolutional Network. Future Internet, 10, Article 54. [Google Scholar] [CrossRef] 
[22] Baluja, S. (2020) Hiding Images within Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 1685-1697. [Google Scholar] [CrossRef] [PubMed]
[23] Das, A., Wahi, J.S., Anand, M., et al. (2021) Multi-Image Steganography Using Deep Neural Networks. arXiv: 2101.00350. [Google Scholar] [CrossRef] 
[24] Lu, S., Wang, R., Zhong, T. and Rosin, P.L. (2021) Large-Capacity Image Steganography Based on Invertible Neural Networks. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 10811-10820. [Google Scholar] [CrossRef] 
[25] Dinh, L., Krueger, D. and Bengio, Y. (2014) NICE: Non-Linear Independent Components Estimation. arXiv: 1410.8516. [Google Scholar] [CrossRef] 
[26] Dinh, L., Sohl-Dickstein, J. and Bengio, S. (2016) Density Estimation Using Real NVP. arXiv: 1605.08803. [Google Scholar] [CrossRef] 
[27] Kingma, D.P. and Dhariwal, P. (2018) Glow: Generative Flow with Invertible 1x1 Convolutions. arXiv: 1807.03039. [Google Scholar] [CrossRef] 
[28] van der Ouderaa, T.F.A. and Worrall, D.E. (2019) Reversible GANs for Memory-Efficient Image-to-Image Translation. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 4715-4723. [Google Scholar] [CrossRef] 
[29] Ardizzone, L., Lüth, C., Kruse, J., et al. (2019) Guided Image Generation with Conditional Invertible Neural Networks. arXiv: 1907.02392. [Google Scholar] [CrossRef] 
[30] Xiao, M., Zheng, S., Liu, C., Wang, Y., He, D., Ke, G., et al. (2020) Invertible Image Rescaling. Computer Vision—ECCV 2020, Glasgow, 23-28 August 2020, 126-144. [Google Scholar] [CrossRef] 
[31] Lugmayr, A., Danelljan, M., Van Gool, L. and Timofte, R. (2020) SRFlow: Learning the Super-Resolution Space with Normalizing Flow. Computer Vision—ECCV 2020, Glasgow, 23-28 August 2020, 715-732. [Google Scholar] [CrossRef] 
[32] Wang, Y., Xiao, M., Liu, C., et al. (2020) Modeling Lost Information in Lossy Image Compression. arXiv: 2006.11999. [Google Scholar] [CrossRef] 
[33] Liu, Y., Qin, Z., Anwar, S., Ji, P., Kim, D., Caldwell, S., et al. (2021) Invertible Denoising Network: A Light Solution for Real Noise Removal. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 13360-13369. [Google Scholar] [CrossRef] 
[34] Al-Husainy, M.A.F. and Uliyan, D.M. (2019) A Secret-Key Image Steganography Technique Using Random Chain Codes. International Journal of Technology, 10, 731-740. [Google Scholar] [CrossRef] 
[35] Almazaydeh, W.I.A. and Sheshadri, H.S. (2018) Image Steganography Using a Dynamic Symmetric Key. 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, 11-12 May 2018, 1507-1513. [Google Scholar] [CrossRef] 
[36] Masud Karim, S.M., Rahman, M.S. and Hossain, M.I. (2011) A New Approach for LSB Based Image Steganography Using Secret Key. 14th International Conference on Computer and Information Technology (ICCIT 2011), Dhaka, 22-24 December 2011, 286-291. [Google Scholar] [CrossRef] 
[37] Kweon, H., Park, J., Woo, S. and Cho, D. (2021) Deep Multi-Image Steganography with Private Keys. Electronics, 10, Article 1906. [Google Scholar] [CrossRef] 
[38] Li, J., Wen, Y. and He, L. (2023) SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 17-24 June 2023, 6153-6162. [Google Scholar] [CrossRef] 
[39] 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. [Google Scholar] [CrossRef] 
[40] Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015) ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115, 211-252. [Google Scholar] [CrossRef] 
[41] Lin, T., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., et al. (2014) Microsoft COCO: Common Objects in Context. Computer Vision—ECCV 2014, Zurich, 6-12 September 2014, 740-755. [Google Scholar] [CrossRef] 
[42] Kingma, D.P. and Ba, J. (2014) Adam: A Method for Stochastic Optimization. arXiv: 1412.6980. [Google Scholar] [CrossRef] 

为你推荐