Abstract
Content-adaptive automatic cost learning frameworks for image steganography based on deep learning can generate a more exquisite embedding probability map within a short time; such methods have reached remarkable security performance compared with conventional handcraft-based methods. However, some issues in deep steganography are not discussed in spatial domain: (1) the key point to the design of generator has not reached clearly; and (2) existing methods are unstable of model training due to vanishing gradient problem. To investigate these issues, this paper proposes a stable GAN (generative adversarial network) for image steganography called UMC-GAN, which presents a redesigned and adjustable nested U-Shape generator and utilizes deep supervision to fuse multiple embedding probability maps to improve security performance. A novel linear-clipped embedding simulator is designed to alleviate vanishing gradient problem at the staircase regions. Extensive experiments and ablation studies show that the proposed method outperforms existing GAN-based automatic cost learning embedding frameworks, and it can be applied at high resolution through the flexible adjustment of the generator. Further investigation on the design of generator is explored by model pruning which shows that in-depth features should be captured for deep steganography to ensure the security performance.
Similar content being viewed by others
References
Fridrich J, Filler T (2007) Practical methods for minimizing embedding impact in steganography. In: Security, Steganography, and Watermarking of Multimedia Contents IX, vol. 6505. San Jose, CA, United States, pp 13–27. https://doi.org/10.1117/12.697471
Filler T, Judas J, Fridrich J (2011) Minimizing additive distortion in steganography using syndrome-trellis codes. IEEE Trans Inf Forensics Secur 6(3):920–935. https://doi.org/10.1109/TIFS.2011.2134094
Pevný T, Filler T, Bas P (2010) Using high-dimensional image models to perform highly undetectable steganography. Inf Hiding. https://doi.org/10.1007/978-3-642-16435-4_13
Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. In: 2012 IEEE International Workshop on Information Forensics and Security (WIFS), pp 234–239. https://doi.org/10.1109/WIFS.2012.6412655
Holub V, Fridrich J, Denemark T (2014) Universal distortion function for steganography in an arbitrary domain. Eurasip J Inf Secur. https://doi.org/10.1186/1687-417X-2014-1
Li B, Wang M, Huang J, Li X (2014) A new cost function for spatial image steganography. In: 2014 IEEE International Conference on Image Processing (ICIP), pp 4206–4210. https://doi.org/10.1109/ICIP.2014.7025854
Sedighi V, Cogranne R, Fridrich J (2016) Content-adaptive steganography by minimizing statistical detectability. IEEE Trans Inf Forensics Secur 11(2):221–234. https://doi.org/10.1109/TIFS.2015.2486744
Westfeld A, Pfitzmann A (2000) Attacks on steganographic systems. Inf Hiding. https://doi.org/10.1007/10719724_5
Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Trans Inf Forensics Secur 7(3):868–882. https://doi.org/10.1109/TIFS.2012.2190402
Denemark T, Sedighi V, Holub V, Cogranne R, Fridrich J (2014) Selection-channel-aware rich model for steganalysis of digital images. In: 2014 IEEE International Workshop on Information Forensics and Security (WIFS), pp 48–53. https://doi.org/10.1109/WIFS.2014.7084302
Kodovsky J, Fridrich J, Holub V (2012) Ensemble classifiers for steganalysis of digital media. IEEE Trans Inf Forensics Secur 7(2):432–444. https://doi.org/10.1109/TIFS.2011.2175919
Qian Y, Dong J, Wang W, Tan T (2016) Learning and transferring representations for image steganalysis using convolutional neural network. In: 2016 IEEE International Conference on Image Processing (ICIP), pp 2752–2756. https://doi.org/10.1109/ICIP.2016.7532860
Xu G, Wu H-Z, Shi Y-Q (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Process Lett 23(5):708–712. https://doi.org/10.1109/LSP.2016.2548421
Xu G, Wu H-Z, Shi YQ (2016) Ensemble of cnns for steganalysis: An empirical study. IH&MMSec ’16, pp 103–107, New York, NY, USA. https://doi.org/10.1145/2909827.2930798
Yang J, Liu K, Kang X, Wong E, Shi Y (2017) Steganalysis based on awareness of selection-channel and deep learning. In: Digital Forensics and Watermarking. https://doi.org/10.1007/978-3-319-64185-0_20
Ye J, Ni J, Yi Y (2017) Deep learning hierarchical representations for image steganalysis. IEEE Trans Inf Forensics Secur 12(11):2545–2557. https://doi.org/10.1109/TIFS.2017.2710946
Yedroudj M, Comby F, Chaumont M (2018) Yedroudj-net: An efficient cnn for spatial steganalysis. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 2092–2096. https://doi.org/10.1109/ICASSP.2018.8461438
Yedroudj M, Chaumont M, Comby F (2018) How to Augment a Small Learning Set for Improving the Performances of a CNN-based Steganalyzer. In: Media Watermarking, Security, and Forensics, IS&T Int. Symp. on Electronic Imaging. https://doi.org/10.2352/ISSN.2470-1173.2018.07.MWSF-317. SF, California, USA
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Li B, Wei W, Ferreira A, Tan S (2018) Rest-net: diverse activation modules and parallel subnets-based cnn for spatial image steganalysis. IEEE Signal Process Lett 25(5):650–654. https://doi.org/10.1109/LSP.2018.2816569
Boroumand M, Chen M, Fridrich J (2019) Deep residual network for steganalysis of digital images. IEEE Trans Inf Forensics Secur 14(5):1181–1193. https://doi.org/10.1109/TIFS.2018.2871749
Tsang CF, Fridrich J (2018) Steganalyzing images of arbitrary size with cnns. In: IS&T International Symposium on Electronic Imaging Science and Technology. https://doi.org/10.2352/ISSN.2470-1173.2018.07.MWSF-121
Yousfi Y, Butora J, Fridrich J, Giboulot Q (2019) Breaking alaska: Color separation for steganalysis in jpeg domain, pp 138–149. https://doi.org/10.1145/3335203.3335727
Butora J, Fridrich J (2020) Reverse jpeg compatibility attack. IEEE Trans Inf Forensics Secur 15:1444–1454. https://doi.org/10.1109/TIFS.2019.2940904
You W, Zhang H, Zhao X (2021) A siamese cnn for image steganalysis. IEEE Trans Inf Forensics Secur 16:291–306. https://doi.org/10.1109/TIFS.2020.3013204
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. NIPS’14, pp 2672–2680. https://doi.org/10.5555/2969033.2969125
Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. IEEE Trans Neural Networks 9(5):1054–1054. https://doi.org/10.1109/TNN.1998.712192
Baluja S (2017) Hiding images in plain sight: Deep steganography. NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp 2066–2076. https://doi.org/10.5555/3294771.3294968
Zhu J, Kaplan R, Johnson J, Fei-Fei L (2018) Hidden: hiding data with deep networks. Computer Vision - ECCV 2018:682–697. https://doi.org/10.1007/978-3-030-01267-0_40
Tang W, Tan S, Li B, Huang J (2017) Automatic steganographic distortion learning using a generative adversarial network. IEEE Signal Process Lett 24(10):1547–1551. https://doi.org/10.1109/LSP.2017.2745572
Yang J, Ruan D, Huang J, Kang X, Shi Y (2020) An embedding cost learning framework using gan. IEEE Trans Inf Forensics Secur 15:839–851. https://doi.org/10.1109/TIFS.2019.2922229
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
Yang J, Ruan D, Kang X, Shi Y-Q (2019) Towards automatic embedding cost learning for jpeg steganography. In: Proceedings of the ACM Workshop on Information Hiding and Multimedia Security. IH&MMSec’19, pp 37–46. https://doi.org/10.1145/3335203.3335713
Tang W, Li B, Barni M, Li J, Huang J (2021) An automatic cost learning framework for image steganography using deep reinforcement learning. IEEE Trans Inf Forensics Secur 16:952–967. https://doi.org/10.1109/TIFS.2020.3025438
Tang W, Li B, Barni M, Li J, Huang J (2021) Improving cost learning for jpeg steganography by exploiting jpeg domain knowledge. arXiv:2105.03867
Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J (2020) Unet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans Med Imaging 39(6):1856–1867. https://doi.org/10.1109/TMI.2019.2959609
Isola P, Zhu J-Y, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5967–5976. https://doi.org/10.1109/CVPR.2017.632
Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In: ICML Workshop on Deep Learning for Audio, Speech and Language Processing
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434
Bas P, Filler T, Pevný T. (2011) ”break our steganographic system”: The ins and outs of organizing boss. In: Information Hiding, pp 59–70. https://doi.org/10.1007/978-3-642-24178-9_5
Acknowledgements
This work is supported by the National Defense Basic Scientific Research Program of China (JCKY2018603B006).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We have no financial and personal relationships with other people or organizations that can inappropriately influence our work; there is no professional or other personal interest of any nature or kind in any product, service or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhao, J., Wang, S. A stable GAN for image steganography with multi-order feature fusion. Neural Comput & Applic 34, 16073–16088 (2022). https://doi.org/10.1007/s00521-022-07270-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07270-w