Fighting deepfakes by detecting GAN DCT anomalies

by   Oliver Giudice, et al.

Synthetic multimedia content created through AI technologies, such as Generative Adversarial Networks (GAN), applied to human faces can bring serious social and political consequences in the private life of every person. State-of-the-art algorithms use deep neural networks to detect a fake content but unfortunately almost all approaches appear to be neither generalizable nor explainable. A new fast detection method able to discriminate Deepfake images with blazing speed and high precision is exposed. By employing Discrete Cosine Transform (DCT), anomalous frequencies in real and Deepfake datasets were analyzed. The βstatistics inferred by the AC coefficients distribution have been the key to recognize GAN-engine generated data. The technique has been validated on pristine high quality faces synthesized by different GANs architectures. Experiments carried out show that the method is innovative, exceeds the state-of-the-art and also gives many insights in terms of explainability.



page 2

page 3

page 4


On the use of Benford's law to detect GAN-generated images

The advent of Generative Adversarial Network (GAN) architectures has giv...

Defending against GAN-based Deepfake Attacks via Transformation-aware Adversarial Faces

Deepfake represents a category of face-swapping attacks that leverage ma...

Pattern Detection in the Activation Space for Identifying Synthesized Content

Generative Adversarial Networks (GANs) have recently achieved unpreceden...

Incremental learning for the detection and classification of GAN-generated images

Current developments in computer vision and deep learning allow to autom...

Do GANs leave artificial fingerprints?

In the last few years, generative adversarial networks (GAN) have shown ...

More Real than Real: A Study on Human Visual Perception of Synthetic Faces

Deep fakes became extremely popular in the last years, also thanks to th...

Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights

Sophisticated generative adversary network (GAN) models are now able to ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.