Deep Learning Approach for Detecting Fake Images Using Transfer Learning

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bolla, Deekshith, Bukaita, Wisam
Format: Recurso digital
Veröffentlicht: Zenodo 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866901511724859392
author Bolla, Deekshith
Bukaita, Wisam
author_facet Bolla, Deekshith
Bukaita, Wisam
contents <p>The increasing sophistication of image manipulation tools poses a significant threat to the credibility of digital visual content. This study presents a deep learning-based classification model for detecting fake images by leveraging transfer learning using the ResNet50 architecture. The model architecture was fine-tuned to perform binary classification between real and synthetically generated images using a balanced dataset comprising 140,002 labeled images. A comprehensive pipeline was designed, including preprocessing steps such as image resizing to 224×224, normalization, augmentation (rotation, flipping, shearing), and validation splitting. The architecture incorporates layers that stabilize training and reduce overfitting while retaining robust feature extraction from the pre-trained base. Initial training yielded 80.85% accuracy and 0.78 F1-score, while post-fine-tuning the model improved to 81.35% accuracy and 88.39% Area Under the Receiver Operating Characteristic Curve, AUC. Empirical evaluations highlight the model's capacity to discern imperceptible manipulation patterns, enabling practical deployment in media forensics and secure image validation systems. Future enhancements may include attention-based classification, adversarial robustness, and region-specific forgery localization.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_16418610
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Deep Learning Approach for Detecting Fake Images Using Transfer Learning
Bolla, Deekshith
Bukaita, Wisam
Image classification
deepfake detection
ResNet50
Transfer learning
image forensics
<p>The increasing sophistication of image manipulation tools poses a significant threat to the credibility of digital visual content. This study presents a deep learning-based classification model for detecting fake images by leveraging transfer learning using the ResNet50 architecture. The model architecture was fine-tuned to perform binary classification between real and synthetically generated images using a balanced dataset comprising 140,002 labeled images. A comprehensive pipeline was designed, including preprocessing steps such as image resizing to 224×224, normalization, augmentation (rotation, flipping, shearing), and validation splitting. The architecture incorporates layers that stabilize training and reduce overfitting while retaining robust feature extraction from the pre-trained base. Initial training yielded 80.85% accuracy and 0.78 F1-score, while post-fine-tuning the model improved to 81.35% accuracy and 88.39% Area Under the Receiver Operating Characteristic Curve, AUC. Empirical evaluations highlight the model's capacity to discern imperceptible manipulation patterns, enabling practical deployment in media forensics and secure image validation systems. Future enhancements may include attention-based classification, adversarial robustness, and region-specific forgery localization.</p>
title Deep Learning Approach for Detecting Fake Images Using Transfer Learning
topic Image classification
deepfake detection
ResNet50
Transfer learning
image forensics
url https://doi.org/10.5281/zenodo.16418610