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.
@article{arxiv.2511.19187,
title = {SpectraNet: FFT-assisted Deep Learning Classifier for Deepfake Face Detection},
author = {Nithira Jayarathne and Naveen Basnayake and Keshawa Jayasundara and Pasindu Dodampegama and Praveen Wijesinghe and Hirushika Pelagewatta and Kavishka Abeywardana and Sandushan Ranaweera and Chamira Edussooriya},
journal= {arXiv preprint arXiv:2511.19187},
year = {2025}
}