TL;DR
This paper introduces a wavelet-packet based method for analyzing and detecting deepfake images, offering a multi-scale, localized approach that improves identification accuracy with lightweight classifiers.
Contribution
It presents a novel wavelet-packet analysis framework for deepfake detection, filling a gap left by pixel-space CNNs and Fourier-based methods, and demonstrates its effectiveness on multiple datasets.
Findings
Wavelet coefficients differ significantly between real and fake images.
Lightweight classifiers using wavelet features achieve competitive detection performance.
The method performs well on datasets like FFHQ, CelebA, LSUN, and FaceForensics++.
Abstract
As neural networks become able to generate realistic artificial images, they have the potential to improve movies, music, video games and make the internet an even more creative and inspiring place. Yet, the latest technology potentially enables new digital ways to lie. In response, the need for a diverse and reliable method toolbox arises to identify artificial images and other content. Previous work primarily relies on pixel-space CNNs or the Fourier transform. To the best of our knowledge, synthesized fake image analysis and detection methods based on a multi-scale wavelet representation, localized in both space and frequency, have been absent thus far. The wavelet transform conserves spatial information to a degree, which allows us to present a new analysis. Comparing the wavelet coefficients of real and fake images allows interpretation. Significant differences are identified.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
