ORCID
- Nathan Clarke: 0000-0002-3595-3800
Abstract
Generative image models pose challenges to image authenticity and trustworthiness, blurring the line between real and fake content. This paper addresses these concerns by proposing a histogram-based approach using pre-trained models (vgg16, ResNet50, Xception) to train classification networks for distinguishing real from generated images. Leveraging histograms derived from images, the method aims to accurately classify images as authentic or synthetic. Through experiments, the paper examines the effectiveness of the approach in mitigating the risks associated with fake contents widespread dissemination. Results demonstrate promising advancements in detecting image manipulation and preserving the integrity of visual information amidst the spread of generative models. Using pre-trained models the paper shows high classification accuracy for detecting fake images.
DOI Link
DOI
10.1016/j.procs.2024.09.382
Publication Date
2024-11-28
Publication Title
Procedia Computer Science
Volume
246
Issue
C
Keywords
Deep Convolutional Neural Networks, Deep Fake Detection, Forgery Detection, Generative Adversarial Networks, Image Forensic
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
First Page
2882
Last Page
2891
Recommended Citation
Hölscher, D., Reich, C., Gut, F., Knahl, M., & Clarke, N. (2024) 'Exploring the Efficacy and Limitations of Histogram-Based Fake Image Detection', Procedia Computer Science, 246(C), pp. 2882-2891. Available at: 10.1016/j.procs.2024.09.382
