FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbations

by   Yonghyun Jeong, et al.
Chung-Ang University

Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise from the overfitting issue, which we discover from our own analysis and the previous studies to originate from the frequency-level artifacts in generated images. We find that ignoring the frequency-level artifacts can improve the detector's generalization across various GAN models, but it can reduce the model's performance for the trained GAN models. Thus, we design a framework to generalize the deepfake detector for both the known and unseen GAN models. Our framework generates the frequency-level perturbation maps to make the generated images indistinguishable from the real images. By updating the deepfake detector along with the training of the perturbation generator, our model is trained to detect the frequency-level artifacts at the initial iterations and consider the image-level irregularities at the last iterations. For experiments, we design new test scenarios varying from the training settings in GAN models, color manipulations, and object categories. Numerous experiments validate the state-of-the-art performance of our deepfake detector.


page 1

page 7


Self-supervised GAN Detector

Although the recent advancement in generative models brings diverse adva...

Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation

GAN-generated image detection now becomes the first line of defense agai...

A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain

We propose a novel universal detector for detecting images generated by ...

Detecting and Simulating Artifacts in GAN Fake Images

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

Black-Box Attack against GAN-Generated Image Detector with Contrastive Perturbation

Visually realistic GAN-generated facial images raise obvious concerns on...

Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective

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

Ensembling with Deep Generative Views

Recent generative models can synthesize "views" of artificial images tha...

Please sign up or login with your details

Forgot password? Click here to reset