Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detection

TL;DR

Wavelet-CLIP is a novel deepfake detection framework that combines wavelet transforms with CLIP-based features, significantly improving generalization and robustness against unseen deepfakes and sophisticated manipulations.

Contribution

This paper introduces Wavelet-CLIP, integrating wavelet analysis with CLIP features to enhance deepfake detection, especially for unseen and complex forgeries.

Findings

Achieves an average AUC of 0.749 in cross-dataset tests

Reaches 0.893 AUC in detecting unseen deepfakes

Outperforms existing state-of-the-art methods in robustness

Abstract

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}