Towards Sustainable Universal Deepfake Detection with Frequency-Domain Masking

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Doloriel, Chandler Timm C., Ullah, Habib, Liland, Kristian Hovde, Machot, Fadi Al, Cheung, Ngai-Man
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912872873852928
author Doloriel, Chandler Timm C.
Ullah, Habib
Liland, Kristian Hovde
Machot, Fadi Al
Cheung, Ngai-Man
author_facet Doloriel, Chandler Timm C.
Ullah, Habib
Liland, Kristian Hovde
Machot, Fadi Al
Cheung, Ngai-Man
contents Universal deepfake detection aims to identify AI-generated images across a broad range of generative models, including unseen ones. This requires robust generalization to new and unseen deepfakes, which emerge frequently, while minimizing computational overhead to enable large-scale deepfake screening, a critical objective in the era of Green AI. In this work, we explore frequency-domain masking as a training strategy for deepfake detectors. Unlike traditional methods that rely heavily on spatial features or large-scale pretrained models, our approach introduces random masking and geometric transformations, with a focus on frequency masking due to its superior generalization properties. We demonstrate that frequency masking not only enhances detection accuracy across diverse generators but also maintains performance under significant model pruning, offering a scalable and resource-conscious solution. Our method achieves state-of-the-art generalization on GAN- and diffusion-generated image datasets and exhibits consistent robustness under structured pruning. These results highlight the potential of frequency-based masking as a practical step toward sustainable and generalizable deepfake detection. Code and models are available at https://github.com/chandlerbing65nm/FakeImageDetection.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08042
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Sustainable Universal Deepfake Detection with Frequency-Domain Masking
Doloriel, Chandler Timm C.
Ullah, Habib
Liland, Kristian Hovde
Machot, Fadi Al
Cheung, Ngai-Man
Computer Vision and Pattern Recognition
Universal deepfake detection aims to identify AI-generated images across a broad range of generative models, including unseen ones. This requires robust generalization to new and unseen deepfakes, which emerge frequently, while minimizing computational overhead to enable large-scale deepfake screening, a critical objective in the era of Green AI. In this work, we explore frequency-domain masking as a training strategy for deepfake detectors. Unlike traditional methods that rely heavily on spatial features or large-scale pretrained models, our approach introduces random masking and geometric transformations, with a focus on frequency masking due to its superior generalization properties. We demonstrate that frequency masking not only enhances detection accuracy across diverse generators but also maintains performance under significant model pruning, offering a scalable and resource-conscious solution. Our method achieves state-of-the-art generalization on GAN- and diffusion-generated image datasets and exhibits consistent robustness under structured pruning. These results highlight the potential of frequency-based masking as a practical step toward sustainable and generalizable deepfake detection. Code and models are available at https://github.com/chandlerbing65nm/FakeImageDetection.
title Towards Sustainable Universal Deepfake Detection with Frequency-Domain Masking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.08042