EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detection of AI-Generated Synthetic Images with a Lightweight CNN

Adrian Lokner Lađević, Tin Kramberger, Renata Kramberger, Dino Vlahek

AI · 03.09.2024 · 5 (3) · 1575-1593

DOI: 10.3390/ai5030076 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 03.09.2024. Verfasst von Adrian Lokner Lađević und 3 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid development of generative adversarial networks has significantly advanced the generation of synthetic images, presenting valuable opportunities and ethical dilemmas in their potential misuse across various industries. The necessity to distinguish real from AI-generated content is becoming increasingly critical to preserve the integrity of online data. While traditional methods for detecting fake images resulting from image tampering rely on hand-crafted features, the sophistication of manipulated images produced by generative adversarial networks requires more advanced detection approaches. The lightweight approach proposed here is based on convolutional neural networks that comprise only eight convolutional and two hidden layers that effectively differentiate AI-generated images from real ones. The proposed approach was assessed using two benchmark datasets and custom-generated data from Sentinel-2 imagery. It demonstrated superior performance compared to four state-of-the-art methods on the CIFAKE dataset, achieving the highest accuracy of 97.32%, on par with the highest-performing state-of-the-art method. Explainable AI is utilized to enhance our comprehension of the complex processes involved in synthetic image recognition. We have shown that, unlike authentic images, where activations often center around the main object, in synthetic images, activations cluster around the edges of objects, in the background, or in areas with complex textures.

Zitieren

APA

Lađević, A. L., Kramberger, T., Kramberger, R., & Vlahek, D. (2024). Detection of AI-Generated Synthetic Images with a Lightweight CNN. AI, 5(3), 1575-1593. https://doi.org/10.3390/ai5030076

Vancouver

Lađević AL, Kramberger T, Kramberger R, Vlahek D. Detection of AI-Generated Synthetic Images with a Lightweight CNN. AI. 2024;5(3):1575-1593. doi:10.3390/ai5030076

BibTeX
@article{Laevi2024,
  author = {Lađević, Adrian Lokner and Kramberger, Tin and Kramberger, Renata and Vlahek, Dino},
  title = {Detection of AI-Generated Synthetic Images with a Lightweight CNN},
  journal = {AI},
  year = {2024},
  volume = {5},
  number = {3},
  pages = {1575--1593},
  doi = {10.3390/ai5030076}
}
Kostenlos starten →