DeepAI AI Chat
Log In Sign Up

Leveraging Frequency Analysis for Deep Fake Image Recognition

by   Joel Frank, et al.

Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements have been largely made possible by Generative Adversarial Networks (GANs). While these deep fake images have been thoroughly investigated in the image domain-a classical approach from the area of image forensics-an analysis in the frequency domain has been missing so far. In this paper, we address this shortcoming and our results reveal that in frequency space, GAN-generated images exhibit severe artifacts that can be easily identified. We perform a comprehensive analysis, showing that these artifacts are consistent across different neural network architectures, data sets, and resolutions. In a further investigation, we demonstrate that these artifacts are caused by upsampling operations found in all current GAN architectures, indicating a structural and fundamental problem in the way images are generated via GANs. Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.


page 4

page 5

page 6

page 13


CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection

In this paper, we propose a novel CycleGAN without checkerboard artifact...

Fake Generated Painting Detection via Frequency Analysis

With the development of deep neural networks, digital fake paintings can...

Detecting and Simulating Artifacts in GAN Fake Images

To detect GAN generated images, conventional supervised machine learning...

Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective

Backdoor attacks have been considered a severe security threat to deep l...

Misleading Deep-Fake Detection with GAN Fingerprints

Generative adversarial networks (GANs) have made remarkable progress in ...

Human Annotations Improve GAN Performances

Generative Adversarial Networks (GANs) have shown great success in many ...

Intriguing properties of synthetic images: from generative adversarial networks to diffusion models

Detecting fake images is becoming a major goal of computer vision. This ...

Code Repositories


Code for the ICML 2020 paper: Leveraging Frequency Analysis for Deep Fake Image Recognition.

view repo