Generalization in Deepfake Detection:
Revista de Informática Teórica e Aplicada · 10.03.2026 · 33 (2) · 243-251
DOI: 10.22456/2175-2745.150900 ↗Kurz gefasst
Fachartikel in der Zeitschrift Revista de Informática Teórica e Aplicada, online erschienen am 10.03.2026. Verfasst von Nathalia Farinha Rodrigues und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This study investigates deepfake detection, a rapidly evolving class of synthetic media with major financial and ethical implications. We evaluate the generalization of two detection approaches: Convolutional Neural Network (CNN)-based models, represented by EfficientNetAutoAttB4, and frequency-domain models, exemplified by FreqNet. While EfficientNetAutoAttB4 achieves strong performance on in-domain data, it tends to overfit, whereas FreqNet captures spectral artifacts that improve robustness to unseen manipulations. Cross-database evaluation on the GANGen-Detection dataset shows that FreqNet consistently outperforms EfficientNet across Accuracy, AUC-ROC, and F1-score. These results highlight the importance of frequency-domain representations for building more generalizable deepfake detectors and expose the limitations of purely spatial CNNs when facing out-of-distribution data. Code and example images to reproduce the experiments are available in the associated repository https://github.com/NathFarinha/deepfake-detection-generalization-efficientnet-freqnet.git.
Zitieren
APA
Rodrigues, N. F., Akabane, A. T., Souza, V. C. D., & Macarini, L. A. B. (2026). Generalization in Deepfake Detection:. Revista de Informática Teórica e Aplicada, 33(2), 243-251. https://doi.org/10.22456/2175-2745.150900
Vancouver
Rodrigues NF, Akabane AT, Souza VCD, Macarini LAB. Generalization in Deepfake Detection:. Revista de Informática Teórica e Aplicada. 2026;33(2):243-251. doi:10.22456/2175-2745.150900
BibTeX
@article{Rodrigues2026,
author = {Rodrigues, Nathalia Farinha and Akabane, Ademar Takeo and Souza, Vinicius Carbonezi de and Macarini, Luiz Antonio Buschetto},
title = {Generalization in Deepfake Detection:},
journal = {Revista de Informática Teórica e Aplicada},
year = {2026},
volume = {33},
number = {2},
pages = {243--251},
doi = {10.22456/2175-2745.150900}
}
EUVIMED