Affiliation:
1. Department of Electrical and Computer Engineering, University of Patras, 265 04 Patras, Greece
2. Department of Digital Media and Communication, Ionian University, 491 00 Argostoli, Greece
Abstract
The emergence of deep learning has sparked notable strides in the quality of synthetic media. Yet, as photorealism reaches new heights, the line between generated and authentic images blurs, raising concerns about the dissemination of counterfeit or manipulated content online. Consequently, there is a pressing need to develop automated tools capable of effectively distinguishing synthetic images, especially those portraying faces, which is one of the most commonly encountered issues. In this work, we propose a novel approach to synthetic face discrimination, leveraging deep learning-based image compression and predominantly utilizing the quality metrics of an image to determine its authenticity.
Reference54 articles.
1. Dogoulis, P., Kordopatis-Zilos, G., Kompatsiaris, I., and Papadopoulos, S. (2023, January 12–15). Improving Synthetically Generated Image Detection in Cross-Concept Settings. Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation (MAD ‘23), Thessaloniki, Greece.
2. Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. (2022). Hierarchical text-conditional image generation with clip latents. arXiv.
3. Generative Adversarial Networks;Goodfellow;Commun. ACM,2020
4. Alias-free generative adversarial networks;Karras;In Adv. Neural Inf. Process. Syst.,2021
5. Diffusion models beat GANs on image synthesis;Dhariwal;Adv. Neural Inf. Process. Syst.,2021