Wavelet-based GAN Fingerprint Detection using ResNet50

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Erukude, Sai Teja, Veluru, Suhasnadh Reddy, Marella, Viswa Chaitanya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911230973706240
author Erukude, Sai Teja
Veluru, Suhasnadh Reddy
Marella, Viswa Chaitanya
author_facet Erukude, Sai Teja
Veluru, Suhasnadh Reddy
Marella, Viswa Chaitanya
contents Identifying images generated by Generative Adversarial Networks (GANs) has become a significant challenge in digital image forensics. This research presents a wavelet-based detection method that uses discrete wavelet transform (DWT) preprocessing and a ResNet50 classification layer to differentiate the StyleGAN-generated images from real ones. Haar and Daubechies wavelet filters are applied to convert the input images into multi-resolution representations, which will then be fed to a ResNet50 network for classification, capitalizing on subtle artifacts left by the generative process. Moreover, the wavelet-based models are compared to an identical ResNet50 model trained on spatial data. The Haar and Daubechies preprocessed models achieved a greater accuracy of 93.8 percent and 95.1 percent, much higher than the model developed in the spatial domain (accuracy rate of 81.5 percent). The Daubechies-based model outperforms Haar, showing that adding layers of descriptive frequency patterns can lead to even greater distinguishing power. These results indicate that the GAN-generated images have unique wavelet-domain artifacts or "fingerprints." The method proposed illustrates the effectiveness of wavelet-domain analysis to detect GAN images and emphasizes the potential of further developing the capabilities of future deepfake detection systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21822
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Wavelet-based GAN Fingerprint Detection using ResNet50
Erukude, Sai Teja
Veluru, Suhasnadh Reddy
Marella, Viswa Chaitanya
Computer Vision and Pattern Recognition
Artificial Intelligence
Identifying images generated by Generative Adversarial Networks (GANs) has become a significant challenge in digital image forensics. This research presents a wavelet-based detection method that uses discrete wavelet transform (DWT) preprocessing and a ResNet50 classification layer to differentiate the StyleGAN-generated images from real ones. Haar and Daubechies wavelet filters are applied to convert the input images into multi-resolution representations, which will then be fed to a ResNet50 network for classification, capitalizing on subtle artifacts left by the generative process. Moreover, the wavelet-based models are compared to an identical ResNet50 model trained on spatial data. The Haar and Daubechies preprocessed models achieved a greater accuracy of 93.8 percent and 95.1 percent, much higher than the model developed in the spatial domain (accuracy rate of 81.5 percent). The Daubechies-based model outperforms Haar, showing that adding layers of descriptive frequency patterns can lead to even greater distinguishing power. These results indicate that the GAN-generated images have unique wavelet-domain artifacts or "fingerprints." The method proposed illustrates the effectiveness of wavelet-domain analysis to detect GAN images and emphasizes the potential of further developing the capabilities of future deepfake detection systems.
title Wavelet-based GAN Fingerprint Detection using ResNet50
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.21822