Abstract
Secure transmission of information across networks is of esteem importance to meet confidentiality and privacy goals and therefore is a huge concern to modern society. To prevent information from being compromised during communication, many steganography or data hiding algorithms have been introduced in recent years. Steganography refers to hiding secret information into cover files like text, images, audio etc., to secure communications. The term Image Steganography is used to describe steganography processes where images are used as cover files. Conventional steganography algorithms are observed to impose high risk of being deciphered by intelligent systems. This paper proposes a system that eliminates such a risk by hiding secret information inside stego images generated using Generative Adversarial Networks (GANs) and then safely reproducing it using an Extractor model. The experimental results of the proposed system demonstrated an accuracy of 92.34% achieved by the extractor model while retrieving the hidden information from the stego images and an overall steganography capacity of 93.75e−3 bytes/pixel for the entire system. Thus, the proposed system reduces the probability of any external intelligent system intercepting the communication and stealing information, like in the case of systems following traditional algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Liu, J., et al.: Recent advances of image steganography with generative adversarial networks. IEEE Access 8, 60575–60597 (2020). https://doi.org/10.1109/ACCESS.2020.2983175
Cachin, C.: An information-theoretic model for steganography. In: Information Hiding, pp. 306–318. Springer, Berlin, Germany (1998). [Online]. Available: https://doi.org/10.1007/3-540-49380-8_21
Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis (2016), [Online]. Available: https://arxiv.org/abs/1605.05396
Volkhonskiy, D., Borisenko, B., Burnaev, E.: Steganographic generative adversarial networks. CoRR abs/1703.05502 (2017), [Online]. Available: http://arxiv.org/abs/1703.05502
Liu, M.-M., Zhang, M.-Q., Liu, J., Gao, P.-X., Zhang, Y.-N.: Coverless information hiding based on generative adversarial networks. Yingyong Kexue Xuebao/J. Appl. Sci. 36, 371–382 (2018). https://doi.org/10.3969/j.issn.0255-8297.2018.02.015
Li, J., Niu, K., Liao, L., Wang, L., Liu, J., Lei, Y., Zhang, M.: A generative steganography method based on WGAN-GP (2020). https://doi.org/10.1007/978-981-15-8083-3_34
Zhang, Z., et al.: Generative steganography by sampling. IEEE Access 7, 118586–118597 (2019). https://doi.org/10.1109/ACCESS.2019.2920313
Zhang, Z., Fu, G., Di, F., Li, C., Liu, J.: Generative reversible data hiding by image-to-image translation via GANs. Secur. Commun. Networks 2019, 1–10 (2019). https://doi.org/10.1155/2019/4932782
Sarkar, T., Sanyal, S.: Reversible and irreversible data hiding technique (2014)
Pibre, L., Jérôme, P., Ienco, D., Chaumont, M.: Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch (2015), [Online]. Available: https://arxiv.org/abs/1511.04855
Ke, Y., Zhang, M., Liu, J., Su, T., Yang, X.: Generative steganography with Kerckhoffs’ principle based on generative adversarial networks (2018). https://arxiv.org/abs/1711.04916
Hu, D., Wang, L., Jiang, W., Zheng, S., Li, B.: A novel image steganography method via deep convolutional generative adversarial networks. IEEE Access 6, 38303–38314 (2018). https://doi.org/10.1109/ACCESS.2018.2852771
Zhou, Z., Sun, H., Harit, R., Chen, X., Sun, X.: Coverless image steganography without embedding. In: Proceedings of International Conference on Cloud Computing Security, pp. 123–132 (2015)
Zhou, Z.-L., Cao, Y., Sun, X.-M.: Coverless information hiding based on bag-of-words model of image. J. Appl. Sci. 34(5), 527–536 (2016)
Zheng, S., Wang, L., Ling, B., Hu, D.: Coverless information hiding based on robust image hashing. In: Intelligent Computing Methodologies, pp. 536–547. Springer, Cham, Switzerland (2017). https://doi.org/10.1007/978-3-319-63315-2_47
Otori, H., Kuriyama, S.: Texture synthesis for mobile data communications. IEEE Comput. Graph. Appl. 29(6), 74–81 (2009)
Xu, J., et al.: Hidden message in a deformation-based texture. Vis. Comput. Int. J. Comput. Graph. 31(12), 1653–1669 (2015)
Wu, K.-C., Wang, C.-M.: Steganography using reversible texture synthesis. IEEE Trans. Image Process. 24(1), 130–139 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Ramaneti, K., Kakani, P., Krishna, C., Rajkumar, S. (2021). Image Steganography Using GANs. In: Lee, R. (eds) Computer and Information Science 2021—Summer . ICIS 2021. Studies in Computational Intelligence, vol 985. Springer, Cham. https://doi.org/10.1007/978-3-030-79474-3_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-79474-3_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79473-6
Online ISBN: 978-3-030-79474-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)