Combating Digitally Altered Images: Deepfake Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kumar, Saksham, Narang, Rhythm
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909754571358208
author Kumar, Saksham
Narang, Rhythm
author_facet Kumar, Saksham
Narang, Rhythm
contents The rise of Deepfake technology to generate hyper-realistic manipulated images and videos poses a significant challenge to the public and relevant authorities. This study presents a robust Deepfake detection based on a modified Vision Transformer(ViT) model, trained to distinguish between real and Deepfake images. The model has been trained on a subset of the OpenForensics Dataset with multiple augmentation techniques to increase robustness for diverse image manipulations. The class imbalance issues are handled by oversampling and a train-validation split of the dataset in a stratified manner. Performance is evaluated using the accuracy metric on the training and testing datasets, followed by a prediction score on a random image of people, irrespective of their realness. The model demonstrates state-of-the-art results on the test dataset to meticulously detect Deepfake images.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16975
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Combating Digitally Altered Images: Deepfake Detection
Kumar, Saksham
Narang, Rhythm
Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
The rise of Deepfake technology to generate hyper-realistic manipulated images and videos poses a significant challenge to the public and relevant authorities. This study presents a robust Deepfake detection based on a modified Vision Transformer(ViT) model, trained to distinguish between real and Deepfake images. The model has been trained on a subset of the OpenForensics Dataset with multiple augmentation techniques to increase robustness for diverse image manipulations. The class imbalance issues are handled by oversampling and a train-validation split of the dataset in a stratified manner. Performance is evaluated using the accuracy metric on the training and testing datasets, followed by a prediction score on a random image of people, irrespective of their realness. The model demonstrates state-of-the-art results on the test dataset to meticulously detect Deepfake images.
title Combating Digitally Altered Images: Deepfake Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2508.16975