DeepFake Detection by Analyzing Convolutional Traces



WORKSHOP ON MEDIA FORENSICS - CVPR 2020



Luca Guarnera1,2, Oliver Giudice1, Sebastiano Battiato1
1 Department of Mathematics and Computer Science, University of Catania, Italy
2 iCTLab s.r.l. Spinoff of University of Catania, Italy
luca.guarnera@unict.it (luca.guarnera@ictlab.srl), {giudice, battiato}@dmi.unict.it









Examples of Deepfake: (a) Obama (Buzzfeed in collaboration with Monkeypaw Studios);
(b) Mark Zuckerberg (Bill Posters and Daniel Howe in partnership with advertising company Canny);
(c) Matteo Renzi (the italian TV program "Striscia la Notizia").



ABSTRACT


The Deepfake phenomenon has become very popular nowadays thanks to the possibility to create incredibly realistic images using deep learning tools, based mainly on ad-hoc Generative Adversarial Networks (GAN). In this work we focus on the analysis of Deepfakes of human faces with the objective of creating a new detection method able to detect a forensics trace hidden in images: a sort of fingerprint left in the image generation process. The proposed technique, by means of an Expectation Maximization (EM) algorithm, extracts a set of local features specifically addressed to model the underlying convolutional generative process. Ad-hoc validation has been employed through experimental tests with naive classifiers on five different architectures (GDWCT, STARGAN, ATTGAN, STYLEGAN, STYLEGAN2) against the CELEBA dataset as ground-truth for non-fakes. Results demonstrated the effectiveness of the technique in distinguishing the different architectures and the corresponding generation process.






Download Paper  

Cite:
@inproceedings{guarnera2020deepfake,
   title={DeepFake Detection by Analyzing Convolutional Traces},
   author={Guarnera, Luca and Giudice, Oliver and Battiato, Sebastiano},
   booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision
   and Pattern Recognition Workshops},
   pages={666--667},
   year={2020}
}






Video Presentation






Experimental Results

This page shows all the results obtained through the tests carried out, not only those shown in the paper but also all the classification parameters considered throughout this work





Results of each comparison

Confusion Matrix t-SNE (two dimensions)




Binary classification (CELEBA Vs DeepNetworks)

Confusion Matrix t-SNE (two dimensions)



Plot accuracy

Accuracy Analysis
Accuracy Analysis - Binary classification (CELEBA Vs DeepNetworks)