DeepGuard: Identification and Attribution of AI-Generated Synthetic Images
Electronics · 08.02.2025 · 14 (4) · 665
DOI: 10.3390/electronics14040665 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 08.02.2025. Verfasst von Yasmine Namani und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Text-to-image (T2I) synthesis, driven by advancements in deep learning and generative models, has seen significant improvements, enabling the creation of highly realistic images from textual descriptions. However, this rapid development brings challenges in distinguishing synthetic images from genuine ones, raising concerns in critical areas such as security, privacy, and digital forensics. To address these concerns and ensure the reliability and authenticity of data, this paper conducts a systematic study on detecting fake images generated by text-to-image synthesis models. Specifically, it evaluates the effectiveness of deep learning methods that leverage ensemble learning for detecting fake images. Additionally, it introduces a multi-classification technique to attribute fake images to their source models, thereby enabling accountability for model misuse. The effectiveness of these methods is assessed through extensive simulations and proof-of-concept experiments. The results reveal that these methods can effectively detect fake images and associate them with their respective generation models, achieving impressive accuracy rates ranging from 98.00% to 99.87% on our custom dataset, “DeepGuardDB”. These findings highlight the potential of the proposed techniques to mitigate synthetic media risks, ensuring a safer digital space with preserved authenticity across various domains, including journalism, legal forensics, and public safety.
Zitieren
APA
Namani, Y., Reghioua, I., Bendiab, G., Labiod, M. A., & Shiaeles, S. (2025). DeepGuard: Identification and Attribution of AI-Generated Synthetic Images. Electronics, 14(4), 665. https://doi.org/10.3390/electronics14040665
Vancouver
Namani Y, Reghioua I, Bendiab G, Labiod MA, Shiaeles S. DeepGuard: Identification and Attribution of AI-Generated Synthetic Images. Electronics. 2025;14(4):665. doi:10.3390/electronics14040665
BibTeX
@article{Namani2025,
author = {Namani, Yasmine and Reghioua, Ikram and Bendiab, Gueltoum and Labiod, Mohamed Aymen and Shiaeles, Stavros},
title = {DeepGuard: Identification and Attribution of AI-Generated Synthetic Images},
journal = {Electronics},
year = {2025},
volume = {14},
number = {4},
pages = {665},
doi = {10.3390/electronics14040665}
}
EUVIMED