# Wavelet-based GAN Fingerprint Detection using ResNet50

arXiv: https://arxiv.org/abs/2510.21822 · HTML: https://mlsanity.com/paper/2510.21822/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Wavelet-Packets for Deepfake Image Analysis and Detection](https://mlsanity.com/paper/2106.09369/) (2021)
- [Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review](https://mlsanity.com/paper/2502.15176/) (2025)
- [Identifying Bias in Deep Neural Networks Using Image Transforms](https://mlsanity.com/paper/2412.13079/) (2024)
- [Identifying bias in CNN image classification using image scrambling and transforms](https://mlsanity.com/paper/2510.10383/) (2025)

## Abstract (arXiv)

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.