Abstract
Training an image steganography is an unsupervised problem, because it is impossible to obtain an ideal supervised steganographic image corresponding to the cover image and secret message. Inspired by the success of cycle generative adversarial networks in unsupervised tasks such as style transfer, this article proposes to use a cycle generative adversarial network to solve the problem of unsupervised image steganography. Specifically, this article jointly trains five networks, i.e., a steganographic network, an inverse steganographic network, a hidden message reconstruction network, and two discriminative networks, which together constitute a hidden message cycle generative adversarial network (HCGAN). Compared with the recent image steganography based on generative adversative network, HCGAN provides more accurate supervised information, which makes the training process of HCGAN converge faster and the performance of the trained image steganography network is better. In addition, this article introduces an image steganographic network based on residual learning and shows that residual learning can effectively improve the performance of steganography. Furthermore, to the best of our knowledge, we are the first to propose an inverse steganographic network for eliminating steganographic message from steganographic images, which can be used to avoid steganographic message being discovered or acquired by a third party. The experimental results show that compared with the steganography based on generative adversarial network, the proposed HCGAN has a higher correct decoding rate, better visual quality of steganographic image, and higher secrecy.
- [1] Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dan Mane, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viegas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, Xiaoqiang Zheng. 2015. TensorFlow: Large-scale machine learning on heterogeneous distributed systems. arXiv: Distributed, parallel, and Cluster Computing (2015). https://arxiv.org/abs/1603.04467.Google Scholar
- [2] . 2016. TensorFlow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI’16). USENIX Association, 265–283. https://www.usenix.org/conference/osdi16/technical-sessions/presentation/abadi.Google Scholar
- [3] . 2012. An introduction to image steganography techniques. In International Conference on Advanced Computer Science Applications and Technologies (ACSAT). IEEE, 122–126.Google Scholar
Digital Library
- [4] . 2004. Hiding data in images by simple LSB substitution. Pattern Recog. 37, 3 (2004), 469–474.Google Scholar
Cross Ref
- [5] . 2014. Generative adversarial nets. In Conference on Advances in Neural Information Processing Systems. 2672–2680.Google Scholar
- [6] . 2017. Generating steganographic images via adversarial training. In Conference on Advances in Neural Information Processing Systems. 1954–1963.Google Scholar
- [7] . 2016. Deep residual learning for image recognition. In Conference on Computer Vision and Pattern Recognition. 770–778.Google Scholar
Cross Ref
- [8] . 2012. Designing steganographic distortion using directional filters. In IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, 234–239.Google Scholar
- [9] . 2013. Digital image steganography using universal distortion. In ACM Workshop on Information Hiding and Multimedia Security. 59–68.Google Scholar
- [10] . 2018. A novel image steganography method via deep convolutional generative adversarial networks. IEEE Access 6 (2018), 38303–38314.Google Scholar
Cross Ref
- [11] . 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning. 448–456.Google Scholar
Digital Library
- [12] . 2017. Image-to-image translation with conditional adversarial networks. In IEEE Conference on Computer Vision and Pattern Recognition. 1125–1134.Google Scholar
Cross Ref
- [13] . 2016. Accurate image super-resolution using very deep convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1646–1654.Google Scholar
- [14] . 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- [15] . 2012. Efficient backprop. In Neural Networks: Tricks of the Trade. Springer, 9–48.Google Scholar
- [16] . 2016. Unsupervised steganalysis based on artificial training sets. Eng. Applic. Artif. Intell. 50 (2016), 45–59.Google Scholar
Digital Library
- [17] . 2014. Investigation on cost assignment in spatial image steganography. IEEE Trans. Inf. Forens. Secur. 9, 8 (2014), 1264–1277.Google Scholar
Digital Library
- [18] . 2015. Deep learning face attributes in the wild. In Proceedings of the IEEE International Conference on Computer Vision. 3730–3738.Google Scholar
Digital Library
- [19] . 2013. Rectifier nonlinearities improve neural network acoustic models. In ICML Workshop on Deep Learning for Audio, Speech and Language Processing, Vol. 30. Citeseer.Google Scholar
- [20] . 2006. LSB matching revisited. IEEE Sig. Process. Lett. 13, 5 (2006), 285–287.Google Scholar
Cross Ref
- [21] . 2010. Using high-dimensional image models to perform highly undetectable steganography. In International Workshop on Information Hiding. Springer, 161–177.Google Scholar
- [22] . 2016. Learning and transferring representations for image steganalysis using convolutional neural network. In IEEE International Conference on Image Processing (ICIP). IEEE, 2752–2756.Google Scholar
Cross Ref
- [23] . 2017. SSGAN: Secure steganography based on generative adversarial networks. In Pacific Rim Conference on Multimedia. 534–544.Google Scholar
- [24] . 2018. Synchronization detection and recovery of steganographic messages with adversarial learning. arXiv preprint arXiv:1801.10365 (2018).Google Scholar
- [25] . 2014. A quantitative analysis of current practices in optical flow estimation and the principles behind them. Int. J. Comput. Vis. 106, 2 (2014), 115–137.Google Scholar
Digital Library
- [26] . 2019. Deep neural networks for efficient steganographic payload location. J. Real-time Image Process. 16, 3 (2019), 635–647.Google Scholar
Digital Library
- [27] . 2013. Anchored neighborhood regression for fast example-based super-resolution. In IEEE International Conference on Computer Vision. 1920–1927.Google Scholar
Digital Library
- [28] . 2014. A+: Adjusted anchored neighborhood regression for fast super-resolution. Asian Conf. Comput. Vis. 9006 (2014), 111–126.Google Scholar
- [29] . 2020. Steganographic generative adversarial networks. In 12th International Conference on Machine Vision (ICMV), Vol. 11433. International Society for Optics and Photonics, 114333M.Google Scholar
Cross Ref
- [30] . 2002. Learning sparse topographic representations with products of student-t distributions. In Conference on Advances in Neural Information Processing Systems. 1383–1390.Google Scholar
- [31] . 2010. On single image scale-up using sparse-representations. In International Conference on Curves and Surfaces. 711–730.Google Scholar
Digital Library
- [32] . 2018. The unreasonable effectiveness of deep features as a perceptual metric. In IEEE Conference on Computer Vision and Pattern Recognition. 586–595.Google Scholar
Cross Ref
- [33] . 2018. Hidden: Hiding data with deep networks. In European Conference on Computer Vision. 657–672.Google Scholar
Digital Library
- [34] . 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In IEEE International Conference on Computer Vision. 2223–2232.Google Scholar
Cross Ref
Index Terms
Hiding Message Using a Cycle Generative Adversarial Network
Recommendations
Generative Steganography Network
MM '22: Proceedings of the 30th ACM International Conference on MultimediaSteganography usually modifies cover media to embed secret data. A new steganographic approach called generative steganography (GS) has emerged recently, in which stego images (images containing secret data) are generated from secret data directly ...
A Novel Grayscale Image Steganography via Generative Adversarial Network
Web Information Systems and ApplicationsAbstractSteganography is an effective technique in the field of information hiding that typically involves embedding secret information into an image to resist steganalysis detection. In recent years, several works on image steganography based on deep ...
Defeating data hiding in social networks using generative adversarial network
AbstractAs a large number of images are transmitted through social networks every moment, terrorists may hide data into images to convey secret data. Various types of images are mixed up in the social networks, and it is difficult for the servers of ...






Comments