Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN Creations

This study proposes a novel forgery detection method based on the analysis of frequency components of images using the Discrete Fourier Transform (DFT). In recent years, face manipulation technologies, particularly Generative Adversarial Networks (GANs), have advanced to such an extent that their mi...

Full description

Saved in:
Bibliographic Details
Main Authors: Vito Nicola Convertini, Donato Impedovo, Ugo Lopez, Giuseppe Pirlo, Gioacchino Sterlicchio
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/15/11/711
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267205825986560
author Vito Nicola Convertini
Donato Impedovo
Ugo Lopez
Giuseppe Pirlo
Gioacchino Sterlicchio
author_facet Vito Nicola Convertini
Donato Impedovo
Ugo Lopez
Giuseppe Pirlo
Gioacchino Sterlicchio
author_sort Vito Nicola Convertini
collection DOAJ
description This study proposes a novel forgery detection method based on the analysis of frequency components of images using the Discrete Fourier Transform (DFT). In recent years, face manipulation technologies, particularly Generative Adversarial Networks (GANs), have advanced to such an extent that their misuse, such as creating deepfakes indistinguishable to human observers, has become a significant societal concern. We reviewed two GAN architectures, StyleGAN and StyleGAN2, generating synthetic faces that were compared with real faces from the FFHQ and CelebA-HQ datasets. The key results demonstrate classification accuracies above 99%, with F1 scores of 99.94% for Support Vector Machines and 97.21% for Random Forest classifiers. These findings underline the fact that performing frequency analysis presents a superior approach to deepfake detection compared to traditional spatial detection methods. It provides insight into subtle manipulation cues in digital images and offers a scalable way to enhance security protocols amid rising digital impersonation threats.
format Article
id doaj-art-8a4e026d96b940a09f0484b39949cbf7
institution OA Journals
issn 2078-2489
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-8a4e026d96b940a09f0484b39949cbf72025-08-20T01:53:53ZengMDPI AGInformation2078-24892024-11-01151171110.3390/info15110711Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN CreationsVito Nicola Convertini0Donato Impedovo1Ugo Lopez2Giuseppe Pirlo3Gioacchino Sterlicchio4Department of Informatics, University of Bari Aldo Moro, 70125 Bari, ItalyDepartment of Informatics, University of Bari Aldo Moro, 70125 Bari, ItalyDepartment of Informatics, University of Bari Aldo Moro, 70125 Bari, ItalyDepartment of Informatics, University of Bari Aldo Moro, 70125 Bari, ItalyDepartment of Mechanics, Mathematics & Management, Polytechnic University of Bari, 70125 Bari, ItalyThis study proposes a novel forgery detection method based on the analysis of frequency components of images using the Discrete Fourier Transform (DFT). In recent years, face manipulation technologies, particularly Generative Adversarial Networks (GANs), have advanced to such an extent that their misuse, such as creating deepfakes indistinguishable to human observers, has become a significant societal concern. We reviewed two GAN architectures, StyleGAN and StyleGAN2, generating synthetic faces that were compared with real faces from the FFHQ and CelebA-HQ datasets. The key results demonstrate classification accuracies above 99%, with F1 scores of 99.94% for Support Vector Machines and 97.21% for Random Forest classifiers. These findings underline the fact that performing frequency analysis presents a superior approach to deepfake detection compared to traditional spatial detection methods. It provides insight into subtle manipulation cues in digital images and offers a scalable way to enhance security protocols amid rising digital impersonation threats.https://www.mdpi.com/2078-2489/15/11/711Generative Adversarial Network (GAN)deepfake detectiondiscrete Fourier transform (DFT)face forgeryStyleGANspectrum analysis
spellingShingle Vito Nicola Convertini
Donato Impedovo
Ugo Lopez
Giuseppe Pirlo
Gioacchino Sterlicchio
Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN Creations
Information
Generative Adversarial Network (GAN)
deepfake detection
discrete Fourier transform (DFT)
face forgery
StyleGAN
spectrum analysis
title Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN Creations
title_full Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN Creations
title_fullStr Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN Creations
title_full_unstemmed Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN Creations
title_short Discrete Fourier Transform in Unmasking Deepfake Images: A Comparative Study of StyleGAN Creations
title_sort discrete fourier transform in unmasking deepfake images a comparative study of stylegan creations
topic Generative Adversarial Network (GAN)
deepfake detection
discrete Fourier transform (DFT)
face forgery
StyleGAN
spectrum analysis
url https://www.mdpi.com/2078-2489/15/11/711
work_keys_str_mv AT vitonicolaconvertini discretefouriertransforminunmaskingdeepfakeimagesacomparativestudyofstylegancreations
AT donatoimpedovo discretefouriertransforminunmaskingdeepfakeimagesacomparativestudyofstylegancreations
AT ugolopez discretefouriertransforminunmaskingdeepfakeimagesacomparativestudyofstylegancreations
AT giuseppepirlo discretefouriertransforminunmaskingdeepfakeimagesacomparativestudyofstylegancreations
AT gioacchinosterlicchio discretefouriertransforminunmaskingdeepfakeimagesacomparativestudyofstylegancreations