Preliminary Forensics Analysis of DeepFake Images


In Proceedings of IEEE AEIT Annual Conference.



Luca Guarnera1,2, Oliver Giudice1, Cristina Nastasi1, Sebastiano Battiato1,2
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








[RELATED WORKS]




Several examples of DeepFake: (a) Obama, created by Buzzfeed in collaboration with Monkeypaw Studios;
(b) Mark Zuckerberg, created by artists Bill Posters and Daniel Howe in partnership with advertising company Canny;
(c) Matteo Renzi, created by "Striscia la Notizia"


ABSTRACT

One of the most terrifying phenomenon nowadays is the Deepfake: the possibility to automatically replace a person's face in images and videos by exploiting algorithms based on deep learning. This paper will present a brief overview of technologies able to produce Deepfake images of faces. A forensics analysis of those images with standard methods will be presented: not surprisingly state of the art techniques are not completely able to detect the fakeness. To solve this, a preliminary idea on how to fight Deepfake images of faces will be presented by analysing anomalies in the frequency domain.





Download Paper  

Cite:
@inproceedings{guarnera2020preliminary,
   title={Preliminary Forensics Analysis of DeepFake Images 2020},
   author={Guarnera, Luca and Giudice, Oliver and Nastasi, Cristina and Battiato, Sebastiano},
   booktitle={Proceedings of IEEE AEIT Annual Conference},
   year={2020},
   organization={IEEE}
}







[RELATED WORKS]