Abstract
Steganography is the strategy of concealing secret data inside images. With the quick advancement of deep learning-based methods in steganalysis, it turns out to be an extremely challenging to design a secure steganographic method. In this paper, we propose a steganographic technique based on GAN, named StegoPix2Pix. In the proposed method U-Net accepts cover image and secret message information as input to synthesize stego-image. This method can effectively withstand steganalysis equipment. Steganalysis cannot identify our stego-images from other generated images using GAN or similar methods. In the meantime, our technique can generate stego-images of arbitrary size with 0.01 bpp, this is an improvement over other steganographic method those, who only can embed fixed-length message information into cover image. Experimental results show that StegoPix2Pix can accomplish security, reliability, and good visual effect.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE J Mag IEEE Xplore. https://ieeexplore.ieee.org/document/6197267. Accessed Apr. 21, 2022
Fridrich J et al (2001) Detecting LSB steganography in color, and gray-scale images. IEEE J Mag IEEE Xplore. https://ieeexplore.ieee.org/document/959097. Accessed Apr. 21, 2022
Goljan M et al (2014) Rich model for Steganalysis of color images. IEEE Conference Publication, IEEE Xplore. https://ieeexplore.ieee.org/document/7084325. Accessed Apr. 21, 2022
Goodfellow IJ et al (2014) Generative adversarial networks. arXiv:1406.2661 [cs, stat]. Accessed Apr. 21, 2022 [Online]. http://arxiv.org/abs/1406.2661
Hayes J, Danezis G (2017) Generating steganographic images via adversarial training. In: Advances in neural information processing systems, vol 30. [Online]. https://papers.nips.cc/paper/2017/hash/fe2d010308a6b3799a3d9c728ee74244-Abstract.html. Accessed Apr. 21, 2022
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
Hu D et al (2018) A novel image steganography method via deep convolutional generative adversarial networks. IEEE J Mag IEEE Xplore. https://ieeexplore.ieee.org/document/8403208. Accessed Apr. 23 2022
Isola P, Zhu J-Y, Zhou T, Efros AA (2018) Image-to-image translation with conditional adversarial networks. arXiv:1611.07004 [cs]. Accessed Apr. 21, 2022 [Online]. http://arxiv.org/abs/1611.07004
Mielikainen J (2006) LSB matching revisited. IEEE Signal Process Lett 13(5):285–287. https://doi.org/10.1109/LSP.2006.870357
Min-ha-zul Abedin Md, Ghosh T, Mehrub T, Yousuf MA (2022) Bangla printed character generation from handwritten character using GAN. In: Soft computing for data analytics, classification model and control, studies in fuzziness and soft computing book series, vol 413. Springer, pp 153–165
Mirza M, Osindero S (2014) [1411.1784] Conditional generative adversarial nets. https://arxiv.org/abs/1411.1784. Accessed Apr. 21, 2022
Pevný T et al (2010) Using high-dimensional image models to perform highly undetectable steganography. SpringerLink. https://link.springer.com/chapter/10.1007/978-3-642-16435-4_13. Accessed Apr. 20, 2022
Qian Y et al (2015) Deep learning for steganalysis via convolutional neural networks. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/9409/94090J/Deep-learning-for-steganalysis-via-convolutional-neural-networks/10.1117/12.2083479.full?SSO=1. Accessed Apr. 21, 2022
Radford A et al (2015) [1511.06434] Unsupervised representation learning with deep convolutional generative adversarial networks. https://arxiv.org/abs/1511.06434. Accessed Apr. 21, 2022
Sazzad S, Rajbongshi A, Shakil R, Akter B, Kaiser MS (2022) RoseNet: rose leave dataset for the development of an automation system to recognize the diseases of rose. Data Brief 44:108497
Shi YQ et al (2007) A Markov process based approach to effective attacking JPEG steganography—New Jersey Institute of Technology. https://researchwith.njit.edu/en/publications/a-markov-process-based-approach-to-effective-attacking-jpeg-stega. Accessed Apr. 21, 2022
Ghosh T, Min-Ha-Zul Abedin Md, Chowdhury SM, Tasnim Z, Karim T, Salim Reza SM, Saika S, Yousuf MA (2020) Bangla handwritten character recognition using MobileNet V1 Architecture. Bull Electr Eng Inform 9(6):2547–2554. https://doi.org/10.11591/eei.v9i6.2234
Ghosh T, Min-Ha-Zul Abedin Md, Hasan Al Banna Md, Mumenin N, Yousuf MA (2021) Performance analysis of state of the art convolutional neural network architectures in Bangla handwritten character recognition. Pattern Recognit Image Anal Springer Link 31(Issue 1):60–71
Zeng J et al (2017) [1611.03233] Large-scale JPEG steganalysis using hybrid deep-learning frame-work. https://arxiv.org/abs/1611.03233. Accessed Apr. 21, 2022
Zheng S et al (2017) Coverless information hiding based on robust image hashing. springerprofes-sional.de. https://www.springerprofessional.de/en/coverless-information-hiding-based-on-robust-image-hashing/13319066. Accessed Apr. 23 2022
Zhu J, Kaplan R, Johnson J, Fei-Fei L (2018) HiDDeN: hiding data with deep networks, arXiv:1807.09937 [cs]. Accessed Apr. 21, 2022 [Online]. http://arxiv.org/abs/1807.09937
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Min-ha-zul Abedin, M., Yousuf, M.A. (2023). StegoPix2Pix: Image Steganography Method via Pix2Pix Networks. In: Kaiser, M.S., Waheed, S., Bandyopadhyay, A., Mahmud, M., Ray, K. (eds) Proceedings of the Fourth International Conference on Trends in Computational and Cognitive Engineering. Lecture Notes in Networks and Systems, vol 618. Springer, Singapore. https://doi.org/10.1007/978-981-19-9483-8_29
Download citation
DOI: https://doi.org/10.1007/978-981-19-9483-8_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-9482-1
Online ISBN: 978-981-19-9483-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)