Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Baru, Lalith Bharadwaj, Boddeda, Rohit, Patel, Shilhora Akshay, Gajapaka, Sai Mohan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909450274603008
author Baru, Lalith Bharadwaj
Boddeda, Rohit
Patel, Shilhora Akshay
Gajapaka, Sai Mohan
author_facet Baru, Lalith Bharadwaj
Boddeda, Rohit
Patel, Shilhora Akshay
Gajapaka, Sai Mohan
contents The evolution of digital image manipulation, particularly with the advancement of deep generative models, significantly challenges existing deepfake detection methods, especially when the origin of the deepfake is obscure. To tackle the increasing complexity of these forgeries, we propose \textbf{Wavelet-CLIP}, a deepfake detection framework that integrates wavelet transforms with features derived from the ViT-L/14 architecture, pre-trained in the CLIP fashion. Wavelet-CLIP utilizes Wavelet Transforms to deeply analyze both spatial and frequency features from images, thus enhancing the model's capability to detect sophisticated deepfakes. To verify the effectiveness of our approach, we conducted extensive evaluations against existing state-of-the-art methods for cross-dataset generalization and detection of unseen images generated by standard diffusion models. Our method showcases outstanding performance, achieving an average AUC of 0.749 for cross-data generalization and 0.893 for robustness against unseen deepfakes, outperforming all compared methods. The code can be reproduced from the repo: \url{https://github.com/lalithbharadwajbaru/Wavelet-CLIP}
format Preprint
id arxiv_https___arxiv_org_abs_2409_18301
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detection
Baru, Lalith Bharadwaj
Boddeda, Rohit
Patel, Shilhora Akshay
Gajapaka, Sai Mohan
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
The evolution of digital image manipulation, particularly with the advancement of deep generative models, significantly challenges existing deepfake detection methods, especially when the origin of the deepfake is obscure. To tackle the increasing complexity of these forgeries, we propose \textbf{Wavelet-CLIP}, a deepfake detection framework that integrates wavelet transforms with features derived from the ViT-L/14 architecture, pre-trained in the CLIP fashion. Wavelet-CLIP utilizes Wavelet Transforms to deeply analyze both spatial and frequency features from images, thus enhancing the model's capability to detect sophisticated deepfakes. To verify the effectiveness of our approach, we conducted extensive evaluations against existing state-of-the-art methods for cross-dataset generalization and detection of unseen images generated by standard diffusion models. Our method showcases outstanding performance, achieving an average AUC of 0.749 for cross-data generalization and 0.893 for robustness against unseen deepfakes, outperforming all compared methods. The code can be reproduced from the repo: \url{https://github.com/lalithbharadwajbaru/Wavelet-CLIP}
title Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2409.18301