Deepfake Image Detection System Using CNN and LSTM
International Journal of Advanced Research in Science Communication and Technology · 11.05.2026 · 321
DOI: 10.48175/ijarsct-35140 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 11.05.2026. Verfasst von Abhishek Subhash Dhanapune and Dr. S. K. Sonkar. Die Arbeit nennt 20 Literaturangaben.
Abstract (Originalsprache)
With the rapid advancement of deep learning, deepfake images have become highly realistic and challenging to detect, posing serious risks in security, social media, and digital forensics. This study proposes a hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) to enhance deepfake detection accuracy. The CNN extracts spatial features from images, while the LSTM captures sequential patterns associated with manipulated content. Trained on a diverse dataset of real and synthetic images, the model achieves high performance, demonstrating its effectiveness for reliable detection in security and forensic applications. This work contributes a robust framework for combating image manipulation and supports future research in deepfake detection.
Zitieren
APA
Sonkar, A. S. D. A. D. S. K. (2026). Deepfake Image Detection System Using CNN and LSTM. International Journal of Advanced Research in Science Communication and Technology, 321. https://doi.org/10.48175/ijarsct-35140
Vancouver
Sonkar ASDADSK. Deepfake Image Detection System Using CNN and LSTM. International Journal of Advanced Research in Science Communication and Technology. 2026:321. doi:10.48175/ijarsct-35140
BibTeX
@article{Sonkar2026,
author = {Sonkar, Abhishek Subhash Dhanapune and Dr. S. K.},
title = {Deepfake Image Detection System Using CNN and LSTM},
journal = {International Journal of Advanced Research in Science Communication and Technology},
year = {2026},
pages = {321},
doi = {10.48175/ijarsct-35140}
}
EUVIMED