SpectraNet: FFT-assisted Deep Learning Classifier for Deepfake Face Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jayarathne, Nithira, Basnayake, Naveen, Jayasundara, Keshawa, Dodampegama, Pasindu, Wijesinghe, Praveen, Pelagewatta, Hirushika, Abeywardana, Kavishka, Ranaweera, Sandushan, Edussooriya, Chamira
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911283855491072
author Jayarathne, Nithira
Basnayake, Naveen
Jayasundara, Keshawa
Dodampegama, Pasindu
Wijesinghe, Praveen
Pelagewatta, Hirushika
Abeywardana, Kavishka
Ranaweera, Sandushan
Edussooriya, Chamira
author_facet Jayarathne, Nithira
Basnayake, Naveen
Jayasundara, Keshawa
Dodampegama, Pasindu
Wijesinghe, Praveen
Pelagewatta, Hirushika
Abeywardana, Kavishka
Ranaweera, Sandushan
Edussooriya, Chamira
contents Detecting deepfake images is crucial in combating misinformation. We present a lightweight, generalizable binary classification model based on EfficientNet-B6, fine-tuned with transformation techniques to address severe class imbalances. By leveraging robust preprocessing, oversampling, and optimization strategies, our model achieves high accuracy, stability, and generalization. While incorporating Fourier transform-based phase and amplitude features showed minimal impact, our proposed framework helps non-experts to effectively identify deepfake images, making significant strides toward accessible and reliable deepfake detection.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19187
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpectraNet: FFT-assisted Deep Learning Classifier for Deepfake Face Detection
Jayarathne, Nithira
Basnayake, Naveen
Jayasundara, Keshawa
Dodampegama, Pasindu
Wijesinghe, Praveen
Pelagewatta, Hirushika
Abeywardana, Kavishka
Ranaweera, Sandushan
Edussooriya, Chamira
Computer Vision and Pattern Recognition
Machine Learning
I.4.9; I.2.10; I.2.6
Detecting deepfake images is crucial in combating misinformation. We present a lightweight, generalizable binary classification model based on EfficientNet-B6, fine-tuned with transformation techniques to address severe class imbalances. By leveraging robust preprocessing, oversampling, and optimization strategies, our model achieves high accuracy, stability, and generalization. While incorporating Fourier transform-based phase and amplitude features showed minimal impact, our proposed framework helps non-experts to effectively identify deepfake images, making significant strides toward accessible and reliable deepfake detection.
title SpectraNet: FFT-assisted Deep Learning Classifier for Deepfake Face Detection
topic Computer Vision and Pattern Recognition
Machine Learning
I.4.9; I.2.10; I.2.6
url https://arxiv.org/abs/2511.19187