Detection Of Ai Generated Images And Videos Using Vision Transformer
International Journal of Drug Delivery Technology · 02.06.2026 · 16 (45s)
DOI: 10.25258/ijddt.16.45s.5 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 02.06.2026. Verfasst von Raj Bharath R und 6 weiteren Autor:innen.
Abstract (Originalsprache)
The explosive increase in the production of synthetic media through deep learning has caused popular anxieties about how Deepfakes may be abused to create misinformation and identify theft along with digital fraud. The current paper provides a solid web-based Deepfake Detection System used to detect manipulated visual imagery in both pictures and videos with the help of a fine-tuned Vision Transformer (ViT) model. The proposed architecture is built on Flask-based web application to provide the real-time inference, to facilitate user authentication that is secure, along with effective media posting. According to the confusion matrix and training analysis, the detection module is based on ViT Base Patch-16/224, test accuracy of 93.28, precision of 0.949, and the F1-score of 0.931. The system further pulls out representative video frames and does a batch inference to correct the timing evaluation. The interface gives a visual representation of prediction confidence to enhance the level of transparency. The experimental assessment shows that the system can effectively differentiate between genuine and fake content, which shows its possibilities of use in computer forensics, social media authentication, and authentication of content authenticity.
Zitieren
APA
R, R. B., S, C., C, S. V. T., S, S. V., R, S., H, A., & R, M. K. (2026). Detection Of Ai Generated Images And Videos Using Vision Transformer. International Journal of Drug Delivery Technology, 16(45s). https://doi.org/10.25258/ijddt.16.45s.5
Vancouver
R RB, S C, C SVT, S SV, R S, H A, et al. Detection Of Ai Generated Images And Videos Using Vision Transformer. International Journal of Drug Delivery Technology. 2026;16(45s). doi:10.25258/ijddt.16.45s.5
BibTeX
@article{R2026,
author = {R, Raj Bharath and S, Charles and C, Sidharth Vijayan T. and S, Sanjai Vasanth and R, Sarabeswaran and H, Adnan and R, Mukesh Kumar},
title = {Detection Of Ai Generated Images And Videos Using Vision Transformer},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {45s},
doi = {10.25258/ijddt.16.45s.5}
}
EUVIMED