Advancing GAN Deepfake Detection: Mixed Datasets and Comprehensive Artifact Analysis

The rapid advancement of synthetic media, while beneficial, has also spawned GAN-generated deepfakes, which pose risks, including misinformation and digital fraud. This paper investigates the detectability of GAN-generated static images, focusing on residual artifacts that are imperceptible to human...

Full description

Saved in:
Bibliographic Details
Main Authors: Tamer Say, Mustafa Alkan, Aynur Kocak
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/2/923
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589216733724672
author Tamer Say
Mustafa Alkan
Aynur Kocak
author_facet Tamer Say
Mustafa Alkan
Aynur Kocak
author_sort Tamer Say
collection DOAJ
description The rapid advancement of synthetic media, while beneficial, has also spawned GAN-generated deepfakes, which pose risks, including misinformation and digital fraud. This paper investigates the detectability of GAN-generated static images, focusing on residual artifacts that are imperceptible to humans but detectable through digital analysis. Our approach introduces three key advancements: (1) a taxonomy for classifying GAN residues in deepfake detection; (2) a unique mixed dataset combining StyleGAN3, ProGAN, and InterfaceGAN to aid cross-model detection research; and (3) a combination of frequency space analysis and RGB color correlation methods to improve artifact detection. Covering three different transform methods, three GAN models, and twelve classification methods, ours is the most comprehensive study of detection of static deepfake face images produced by GANs. Our results demonstrate that artifact-based detection can achieve high accuracy, precision, recall, and F1 scores, challenging prior assumptions about the detectability of synthetic face images.
format Article
id doaj-art-c60f4161157647a4b838d022393b0447
institution Kabale University
issn 2076-3417
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-c60f4161157647a4b838d022393b04472025-01-24T13:21:21ZengMDPI AGApplied Sciences2076-34172025-01-0115292310.3390/app15020923Advancing GAN Deepfake Detection: Mixed Datasets and Comprehensive Artifact AnalysisTamer Say0Mustafa Alkan1Aynur Kocak2Department of Information Security Engineering, Graduate School of Natural and Applied Sciences, Gazi University, 06560 Ankara, TurkeyDepartment of Electrical and Electronics Engineering, Faculty of Technology, Gazi University, 06560 Ankara, TurkeyDepartment of Electrical and Electronics Engineering, Faculty of Technology, Gazi University, 06560 Ankara, TurkeyThe rapid advancement of synthetic media, while beneficial, has also spawned GAN-generated deepfakes, which pose risks, including misinformation and digital fraud. This paper investigates the detectability of GAN-generated static images, focusing on residual artifacts that are imperceptible to humans but detectable through digital analysis. Our approach introduces three key advancements: (1) a taxonomy for classifying GAN residues in deepfake detection; (2) a unique mixed dataset combining StyleGAN3, ProGAN, and InterfaceGAN to aid cross-model detection research; and (3) a combination of frequency space analysis and RGB color correlation methods to improve artifact detection. Covering three different transform methods, three GAN models, and twelve classification methods, ours is the most comprehensive study of detection of static deepfake face images produced by GANs. Our results demonstrate that artifact-based detection can achieve high accuracy, precision, recall, and F1 scores, challenging prior assumptions about the detectability of synthetic face images.https://www.mdpi.com/2076-3417/15/2/923computer visiondeepfakessynthetic mediamachine learning
spellingShingle Tamer Say
Mustafa Alkan
Aynur Kocak
Advancing GAN Deepfake Detection: Mixed Datasets and Comprehensive Artifact Analysis
Applied Sciences
computer vision
deepfakes
synthetic media
machine learning
title Advancing GAN Deepfake Detection: Mixed Datasets and Comprehensive Artifact Analysis
title_full Advancing GAN Deepfake Detection: Mixed Datasets and Comprehensive Artifact Analysis
title_fullStr Advancing GAN Deepfake Detection: Mixed Datasets and Comprehensive Artifact Analysis
title_full_unstemmed Advancing GAN Deepfake Detection: Mixed Datasets and Comprehensive Artifact Analysis
title_short Advancing GAN Deepfake Detection: Mixed Datasets and Comprehensive Artifact Analysis
title_sort advancing gan deepfake detection mixed datasets and comprehensive artifact analysis
topic computer vision
deepfakes
synthetic media
machine learning
url https://www.mdpi.com/2076-3417/15/2/923
work_keys_str_mv AT tamersay advancinggandeepfakedetectionmixeddatasetsandcomprehensiveartifactanalysis
AT mustafaalkan advancinggandeepfakedetectionmixeddatasetsandcomprehensiveartifactanalysis
AT aynurkocak advancinggandeepfakedetectionmixeddatasetsandcomprehensiveartifactanalysis