A Study on Deep Fake Image Detection using ELA and Machine Learning
International Journal of Innovative Research in Information Security · 30.04.2024 · 10 (03) · 314-319
DOI: 10.26562/ijiris.2024.v1003.33 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Research in Information Security, online erschienen am 30.04.2024. Verfasst von Adnan Akram und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Deepfake or fabricated images have become extremely realistic that it is impossible to simply distinguish a real image from a deepfake one with the naked eye. Technology has evolved greatly in this area that allows people to have easy access to tools that help them easily create very realistic deepfakes. These modified images are then used for the purposes of identity theft, fraud, dissemination of false information, etc. Not everyone uses these tools in a negative way, many use this technology for good. Some of the good applications can be found in the filmmaking, animation, and video game industry. Due to malicious uses of manipulated media, there is a need for effective tools to detect them. In this study, we make use of the Error Level Analysis Algorithm to pre-process the image and then pass it on to CNN where we train the model and classify the image as genuine or fake.
Zitieren
APA
Akram, A., & Chaitanya, V. (2024). A Study on Deep Fake Image Detection using ELA and Machine Learning. International Journal of Innovative Research in Information Security, 10(03), 314-319. https://doi.org/10.26562/ijiris.2024.v1003.33
Vancouver
Akram A, Chaitanya V. A Study on Deep Fake Image Detection using ELA and Machine Learning. International Journal of Innovative Research in Information Security. 2024;10(03):314-319. doi:10.26562/ijiris.2024.v1003.33
BibTeX
@article{Akram2024,
author = {Akram, Adnan and Chaitanya, Vishwa},
title = {A Study on Deep Fake Image Detection using ELA and Machine Learning},
journal = {International Journal of Innovative Research in Information Security},
year = {2024},
volume = {10},
number = {03},
pages = {314--319},
doi = {10.26562/ijiris.2024.v1003.33}
}
EUVIMED