Evaluating Deepfake Detectors in the Wild

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pirogov, Viacheslav, Artemev, Maksim
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913974035939328
author Pirogov, Viacheslav
Artemev, Maksim
author_facet Pirogov, Viacheslav
Artemev, Maksim
contents Deepfakes powered by advanced machine learning models present a significant and evolving threat to identity verification and the authenticity of digital media. Although numerous detectors have been developed to address this problem, their effectiveness has yet to be tested when applied to real-world data. In this work we evaluate modern deepfake detectors, introducing a novel testing procedure designed to mimic real-world scenarios for deepfake detection. Using state-of-the-art deepfake generation methods, we create a comprehensive dataset containing more than 500,000 high-quality deepfake images. Our analysis shows that detecting deepfakes still remains a challenging task. The evaluation shows that in fewer than half of the deepfake detectors tested achieved an AUC score greater than 60%, with the lowest being 50%. We demonstrate that basic image manipulations, such as JPEG compression or image enhancement, can significantly reduce model performance. All code and data are publicly available at https://github.com/SumSubstance/Deepfake-Detectors-in-the-Wild.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21905
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Deepfake Detectors in the Wild
Pirogov, Viacheslav
Artemev, Maksim
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Deepfakes powered by advanced machine learning models present a significant and evolving threat to identity verification and the authenticity of digital media. Although numerous detectors have been developed to address this problem, their effectiveness has yet to be tested when applied to real-world data. In this work we evaluate modern deepfake detectors, introducing a novel testing procedure designed to mimic real-world scenarios for deepfake detection. Using state-of-the-art deepfake generation methods, we create a comprehensive dataset containing more than 500,000 high-quality deepfake images. Our analysis shows that detecting deepfakes still remains a challenging task. The evaluation shows that in fewer than half of the deepfake detectors tested achieved an AUC score greater than 60%, with the lowest being 50%. We demonstrate that basic image manipulations, such as JPEG compression or image enhancement, can significantly reduce model performance. All code and data are publicly available at https://github.com/SumSubstance/Deepfake-Detectors-in-the-Wild.
title Evaluating Deepfake Detectors in the Wild
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.21905