Trustworthy Deepfake Detection: Explainable LIME Method of ViT and CNN Architectures
Authors
Zoulikha Koudad
zoulikha.Koudad@essa-tlemcen.dz
Department of First Cycle, École Supérieure en Sciences Appliquées de Tlemcen ESSAT, Tlemcen, Algeria
LRIT Laboratory, Faculty of Science, University of Tlemcen, Tlemcen, Algeria
Amina Bekkouche
amina.bekkouche@univ-tlemcen.dz
Department of Computer Science, Faculty of Science, University of Tlemcen, Tlemcen, Algeria
LRIT Laboratory, Faculty of Science, University of Tlemcen, Tlemcen, Algeria
Hamed Benahmed
hamed.benahmed@univ-tlemcen.dz
Department of Computer Science, Faculty of Science, University of Tlemcen, Tlemcen, Algeria
LRIT Laboratory, Faculty of Science, University of Tlemcen, Tlemcen, Algeria
Mourad Hadjila
mourad.hadjila@univ-tlemcen.dz
Department of Telecommunication, Faculty of Technology, University of Tlemcen, Tlemcen, Algeria
STIC Laboratory, Faculty of Technology, University of Tlemcen, Tlemcen, Algeria
Mohammed Merzoug
mohammed.merzoug@univ-tlemcen.dz
Department of Computer Science, Faculty of Science, University of Tlemcen, Tlemcen, Algeria
LRIT Laboratory, Faculty of Science, University of Tlemcen, Tlemcen, Algeria
Language: English
Page range: 61 - 78
Submitted on: Dec 16, 2025
Accepted on: Mar 5, 2026
Published on: Jun 13, 2026
In partnership with: Paradigm Publishing Services
Keywords:
Related subjects:
© 2026 Zoulikha Koudad, Amina Bekkouche, Hamed Benahmed, Mourad Hadjila, Mohammed Merzoug, published by Bulgarian Academy of Sciences, Institute of Information and Communication Technologies
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.