EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

A convolutional neural network-long short-term memory deep learning classification framework for deepfake detection

Mohd Khaled Y. Shambour, Fadwa Feras Abu Hara, Basil Mohammed Abu-taleb, Mohammad Hassan Ali Al-Onaizan, Mohammad Klaib

Bulletin of Electrical Engineering and Informatics · 01.12.2026 · 15 (6) · 5136-5148

DOI: 10.11591/eei.v15i6.11675 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bulletin of Electrical Engineering and Informatics, online erschienen am 01.12.2026. Verfasst von Mohd Khaled Y. Shambour und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The credibility of digital media is being greatly undermined by the rise of deepfake (DF) technology. To help solve this issue, this paper proposes a hybrid spatiotemporal deep learning model that combines the ResNeXt50 convolutional backbone and the long short-term memory (LSTM) model to capture both frame-level spatial artifacts and temporal inconsistencies across video sequences. The novelty of this paper lies in the development of a lightweight convolutional neural network (CNN)-LSTM model that integrates selective fine-tuning of ResNeXt50 with mean-based temporal pooling, enabling improved generalization and computational efficiency for robust DF detection in real-world scenarios. The model was trained and evaluated on the WildDF dataset of 42,456 video sequences. Experimental results revealed that the proposed CNN-LSTM outperformed five baseline models, achieving 79.54% accuracy, 75.80% precision, 73.78% recall, and an F1-score of 74.77%. The proposed approach provides a practical framework for combining spatial and temporal information in DF detection while maintaining a lightweight architecture. This framework can serve as an intelligent classification component within an advanced intelligent classification system, supporting automated and reliable identification of manipulated visual content.

Zitieren

APA

Shambour, M. K. Y., Hara, F. F. A., Abu-taleb, B. M., Al-Onaizan, M. H. A., & Klaib, M. (2026). A convolutional neural network-long short-term memory deep learning classification framework for deepfake detection. Bulletin of Electrical Engineering and Informatics, 15(6), 5136-5148. https://doi.org/10.11591/eei.v15i6.11675

Vancouver

Shambour MKY, Hara FFA, Abu-taleb BM, Al-Onaizan MHA, Klaib M. A convolutional neural network-long short-term memory deep learning classification framework for deepfake detection. Bulletin of Electrical Engineering and Informatics. 2026;15(6):5136-5148. doi:10.11591/eei.v15i6.11675

BibTeX
@article{Shambour2026,
  author = {Shambour, Mohd Khaled Y. and Hara, Fadwa Feras Abu and Abu-taleb, Basil Mohammed and Al-Onaizan, Mohammad Hassan Ali and Klaib, Mohammad},
  title = {A convolutional neural network-long short-term memory deep learning classification framework for deepfake detection},
  journal = {Bulletin of Electrical Engineering and Informatics},
  year = {2026},
  volume = {15},
  number = {6},
  pages = {5136--5148},
  doi = {10.11591/eei.v15i6.11675}
}
Kostenlos starten →