AI vs. AI: Can AI Detect AI-Generated Images?
Journal of Imaging · 28.09.2023 · 9 (10) · 199
DOI: 10.3390/jimaging9100199 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 28.09.2023. Verfasst von Samah S Baraheem und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Umm Al-Qura University, Prince Sultan Bin Abdulaziz Road, Mecca 21421, Makkah, Saudi Arabia. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, University of Dayton Libraries Open Access Fund, NSF.
Abstract (Originalsprache)
The proliferation of Artificial Intelligence (AI) models such as Generative Adversarial Networks (GANs) has shown impressive success in image synthesis. Artificial GAN-based synthesized images have been widely spread over the Internet with the advancement in generating naturalistic and photo-realistic images. This might have the ability to improve content and media; however, it also constitutes a threat with regard to legitimacy, authenticity, and security. Moreover, implementing an automated system that is able to detect and recognize GAN-generated images is significant for image synthesis models as an evaluation tool, regardless of the input modality. To this end, we propose a framework for reliably detecting AI-generated images from real ones through Convolutional Neural Networks (CNNs). First, GAN-generated images were collected based on different tasks and different architectures to help with the generalization. Then, transfer learning was applied. Finally, several Class Activation Maps (CAM) were integrated to determine the discriminative regions that guided the classification model in its decision. Our approach achieved 100% on our dataset, i.e., Real or Synthetic Images (RSI), and a superior performance on other datasets and configurations in terms of its accuracy. Hence, it can be used as an evaluation tool in image generation. Our best detector was a pre-trained EfficientNetB4 fine-tuned on our dataset with a batch size of 64 and an initial learning rate of 0.001 for 20 epochs. Adam was used as an optimizer, and learning rate reduction along with data augmentation were incorporated.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, Umm Al-Qura University, Prince Sultan Bin Abdulaziz Road, Mecca 21421, Makkah, Saudi Arabia.
- Department of Computer Science, University of Dayton, Dayton, OH 45469, USA.
ORCID-Profile: Samah S Baraheem, Tam V Nguyen
Förderung
- National Science Foundation
- University of Dayton Libraries Open Access Fund
- NSF
Zitieren
APA
Baraheem, S. S., & Nguyen, T. V. (2023). AI vs. AI: Can AI Detect AI-Generated Images?. Journal of Imaging, 9(10), 199. https://doi.org/10.3390/jimaging9100199
Vancouver
Baraheem SS, Nguyen TV. AI vs. AI: Can AI Detect AI-Generated Images?. Journal of Imaging. 2023;9(10):199. doi:10.3390/jimaging9100199
BibTeX
@article{Baraheem2023,
author = {Baraheem, Samah S and Nguyen, Tam V},
title = {AI vs. AI: Can AI Detect AI-Generated Images?},
journal = {Journal of Imaging},
year = {2023},
volume = {9},
number = {10},
pages = {199},
doi = {10.3390/jimaging9100199}
}
EUVIMED