Secure Image Generation Using GANs and VAEs: Integrating Robust Security Measures against Adversarial Threats

Gunda Satish Kumar

Abstract


Evaluation of the generated images employs quantitative metrics such as Inception Score (IS) and Frechet Inception Distance (FID) to assess their quality and fidelity. IS measures the diversity and realism of images based on class distributions, while FID quantifies the similarity in feature distributions between generated and real images, providing insights into the effectiveness of the generative models. To fortify the integrity of generated content, the research advances security measures including adversarial input detection algorithms, authentication mechanisms such as digital signatures and watermarking, and encryption techniques like AES for secure data transmission and storage. These measures are integrated directly into the generative model architecture, validated through rigorous testing against adversarial attacks and real-world simulations to ensure robust performance. Research outcomes highlight significant advancements in detecting manipulated images and enhancing the reliability of generative models in diverse applications. The findings contribute to the evolving landscape of secure image generation technologies, offering insights and recommendations for future research directions aimed at advancing the intersection of generative models and cybersecurity.

References


J. Vice, N. Akhtar, R. Hartley and A. Mian, "BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models," in IEEE Transactions on Information Forensics and Security, vol. 19, pp. 4865-4880, 2024, doi: 10.1109/TIFS.2024.3386058.

A. Pavate, R. Bansode, P. N. Srinivasu, J. Shafi, J. Choi and M. F. Ijaz, "Associative Discussion Among Generating Adversarial Samples Using Evolutionary Algorithm and Samples Generated Using GAN," in IEEE Access, vol. 11, pp. 143757-143770, 2023, doi: 10.1109/ACCESS.2023.3343754.

L. Laishram, M. Shaheryar, J. T. Lee and S. K. Jung, "High-Quality Face Caricature via Style Translation," in IEEE Access, vol. 11, pp. 138882-138896, 2023, doi: 10.1109/ACCESS.2023.3340788.

D. Park, H. Na and D. Choi, "Performance Comparison and Visualization of AI-Generated-Image Detection Methods," in IEEE Access, vol. 12, pp. 62609-62627, 2024, doi: 10.1109/ACCESS.2024.3394250.

J. Park, L. H. Park, H. E. Ahn and T. Kwon, "Coexistence of Deepfake Defenses: Addressing the Poisoning Challenge," in IEEE Access, vol. 12, pp. 11674-11687, 2024, doi: 10.1109/ACCESS.2024.3353785.

Y. Zhou, P. He, W. Li, Y. Cao and X. Jiang, "Generalized Fake Image Detection Method Based on Gated Hierarchical Multi-Task Learning," in IEEE Signal Processing Letters, vol. 30, pp. 1767-1771, 2023, doi: 10.1109/LSP.2023.3336570.

W. Quan, P. Deng, K. Wang and D. -M. Yan, "CGFormer: ViT-Based Network for Identifying Computer-Generated Images With Token Labeling," in IEEE Transactions on Information Forensics and Security, vol. 19, pp. 235-250, 2024, doi: 10.1109/TIFS.2023.3322083.


Full Text: PDF [Full Text]

Refbacks

  • There are currently no refbacks.


Copyright © 2013, All rights reserved.| ijseat.com

Creative Commons License
International Journal of Science Engineering and Advance Technology is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJSEat , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.

Â