Utilizing Generative Adversarial Networks for Enhancing Cybersecurity in Image Transmission

Authors

  • Sashikanth Reddy Avula, Jagadish R. M., Krishna Kumar, Shweta Salunkhe, Gopala Varma Kosuri, Suraj Rajesh Karpe

Keywords:

Generative Adversarial Networks (GANs), cybersecurity, image transmission, encryption, authentication, anomaly detection, Fréchet Inception Distance (FID), machine learning.

Abstract

As for the aspect of image confidentiality in the area of digital communication, there are significant problems that are connected with the questions of security because the images can be intercepted and forged. In this paper, a new approach to improving cybersecurity in image transmission has been proposed: Generative Adversarial Networks (GANs). This research seeks to address these challenges by employing GANs to encrypt the images, authenticate them and detect the anomalies in real-time transmission. The process entails the use of GAN architecture with generator and discriminator where the generator is trained on a diverse image dataset, later on the trained model is evaluated using parameters like IS and FID. The results of GANs’ assessment are 98.  5% of success rate in encryption, 97.  8% of accuracy in authentication and 95.  4% of accuracy in anomaly detection, which indicates that GANs can improve the security of image transmission. This research is applicable to the improvement of cybersecurity solutions and the integration of advanced machine learning techniques to counteract new threats to the transmission of digital images.

Downloads

Download data is not yet available.

References

J. Hayes and G. Danezis, "Generating steganographic images via adversarial training," in Advances in Neural Information Processing Systems 30, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, and N. Cesa-Bianchi, Eds. 2017, pp. 1951-1960.

L. Huang, A. D. Joseph, B. Nelson, B. I. Rubinstein, and J. Tygar, "Adversarial Machine Learning," in Proceedings of the 4th ACM Workshop on Security and Artificial Intelligence, 2011, pp. 43-58.

I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Farley, P. Ham, and A. van der Maaten, "Generative adversarial nets," in Advances in Neural Information Processing Systems, 2014, pp. 2672-2680.

J. Zhu, R. Kaplan, J. Johnson, and L. Fei-Fei, "Hidden: Hiding data with deep networks," in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 657-672.

T. S. Reinel, R. P. Raul, and I. Gustavo, "Deep Learning Applied to Steganalysis of Digital Images: A Systematic Review," IEEE Access, vol. 7, pp. 68970-68990, 2019. [Online]. Available: https://doi.org/10.1109/access.2019.2918086

M. Chaumont, "Deep Learning in steganography and steganalysis from 2015 to 2018," arXiv.org, Mar. 31, 2019. [Online]. Available: https://arxiv.org/abs/1904.01444

I. Goodfellow et al., "Generative Adversarial Nets," in Advances in Neural Information Processing Systems, 2014, pp. 2672-2680.

S. Chen, D. Shi, M. Sadiq, and X. Cheng, "Image Denoising With Generative Adversarial Networks and its Application to Cell Image Enhancement," IEEE Access, vol. 8, pp. 82819-82831, 2020. [Online]. Available: https://doi.org/10.1109/access.2020.2988284

S. Sabnam and S. Rajagopal, "Application of generative adversarial networks in image, face reconstruction and medical imaging: challenges and the current progress," Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, vol. 12, no. 1, 2024. [Online]. Available: https://doi.org/10.1080/21681163.2024.2330524

T. Schlegl, P. Seeböck, S. M. Waldstein, U. Schmidt-Erfurth, and G. Langs, "Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery," arXiv.org, Mar. 17, 2017. [Online]. Available: https://arxiv.org/abs/1703.05921

T. Salimans et al., "Improved Techniques for Training GANs," [Online]. Available: https://papers.nips.cc/paper_files/paper/2016/hash/8a3363abe792db2d8761d6403605aeb7-Abstract.html

M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, "GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium," arXiv.org, June 26, 2017. [Online]. Available: https://arxiv.org/abs/1706.08500

M. Arjovsky, S. Chintala, and L. Bottou, "Wasserstein GAN," arXiv.org, Jan. 26, 2017. [Online]. Available: https://arxiv.org/abs/1701.07875

T. Karras, T. Aila, S. Laine, and J. Lehtinen, "Progressive Growing of GANs for Improved Quality, Stability, and Variation," arXiv.org, Oct. 27, 2017. [Online]. Available: https://arxiv.org/abs/1710.10196

H. Xu, C. Caramanis, and S. Mannor, "Robustness and Regularization of Support Vector Machines," arXiv.org, Mar. 25, 2008. [Online]. Available: https://arxiv.org/abs/0803.3490

B. Benjdira, A. Ammar, A. Koubâa, and K. Ouni, "Data-Efficient Domain Adaptation for Semantic Segmentation of Aerial Imagery Using Generative Adversarial Networks," Applied Sciences, vol. 10, no. 3, p. 1092, 2020. [Online]. Available: https://doi.org/10.3390/app10031092

"Figure 7 Accuracy Rate of MLP," ResearchGate. [Online]. Available: https://www.researchgate.net/ figure/Accuracy-Rate-of-MLP-visualized-the-graph-of-training-loss-and-the-validation-loss_fig2_343304832

Downloads

Published

09.07.2024

How to Cite

Sashikanth Reddy Avula. (2024). Utilizing Generative Adversarial Networks for Enhancing Cybersecurity in Image Transmission. International Journal of Intelligent Systems and Applications in Engineering, 12(22s), 1702–1711. Retrieved from https://www.ijisae.org/index.php/IJISAE/article/view/6721

Issue

Vol. 12 No. 22s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.