Corpus ID: 213175447

Leveraging Frequency Analysis for Deep Fake Image Recognition

@article{Frank2020LeveragingFA,
  title={Leveraging Frequency Analysis for Deep Fake Image Recognition},
  author={J. Frank and Thorsten Eisenhofer and Lea Sch{\"o}nherr and Asja Fischer and D. Kolossa and T. Holz},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.08685}
}
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 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… Expand
FakeRetouch: Evading DeepFakes Detection via the Guidance of Deliberate Noise
Are High-Frequency Components Beneficial for Training of Generative Adversarial Networks
DeepTag: Robust Image Tagging for DeepFake Provenance.
Face Forensics in the Wild
Evading Deepfake-Image Detectors with White- and Black-Box Attacks
  • Nicholas Carlini, H. Farid
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2020
A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 60 REFERENCES
Detecting GAN generated Fake Images using Co-occurrence Matrices
Detection of GAN-Generated Fake Images over Social Networks
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
Do GANs Leave Artificial Fingerprints?
Fake Faces Identification via Convolutional Neural Network
Detecting GAN-generated Imagery using Color Cues
GAN is a friend or foe?: a framework to detect various fake face images
Evading Deepfake-Image Detectors with White- and Black-Box Attacks
  • Nicholas Carlini, H. Farid
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2020
CNN-Generated Images Are Surprisingly Easy to Spot… for Now
...
1
2
3
4
5
...