Recent advances in visual media technology have led to new tools for processing and, above all, generating multimedia contents. In particular, modern AI-based technologies have provided easy-to-use tools to create extremely realistic manipulated videos. Such synthetic videos, named Deep Fakes, may constitute a serious threat to attack the reputation of public subjects or to address the general opinion on a certain event. According to this, being able to individuate this kind of fake information becomes fundamental. In this work, a new forensic technique able to discern between fake and original video sequences is given; unlike other state-of-the-art methods which resorts at single video frames, we propose the adoption of optical flow fields to exploit possible inter-frame dissimilarities. Such a clue is then used as feature to be learned by CNN classifiers. Preliminary results obtained on FaceForensics++ dataset highlight very promising performances.

Deepfake Video Detection through Optical Flow Based CNN / Amerini, Irene; Galteri, Leonardo; Caldelli, Roberto; Del Bimbo, Alberto. - (2019), pp. 1205-1207. (Intervento presentato al convegno The IEEE International Conference on Computer Vision (ICCV) Workshops tenutosi a Seoul; Korea) [10.1109/ICCVW.2019.00152].

Deepfake Video Detection through Optical Flow Based CNN

Irene Amerini
;
2019

Abstract

Recent advances in visual media technology have led to new tools for processing and, above all, generating multimedia contents. In particular, modern AI-based technologies have provided easy-to-use tools to create extremely realistic manipulated videos. Such synthetic videos, named Deep Fakes, may constitute a serious threat to attack the reputation of public subjects or to address the general opinion on a certain event. According to this, being able to individuate this kind of fake information becomes fundamental. In this work, a new forensic technique able to discern between fake and original video sequences is given; unlike other state-of-the-art methods which resorts at single video frames, we propose the adoption of optical flow fields to exploit possible inter-frame dissimilarities. Such a clue is then used as feature to be learned by CNN classifiers. Preliminary results obtained on FaceForensics++ dataset highlight very promising performances.
2019
The IEEE International Conference on Computer Vision (ICCV) Workshops
deepfake; opticalflow; cnn; image forensics
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Deepfake Video Detection through Optical Flow Based CNN / Amerini, Irene; Galteri, Leonardo; Caldelli, Roberto; Del Bimbo, Alberto. - (2019), pp. 1205-1207. (Intervento presentato al convegno The IEEE International Conference on Computer Vision (ICCV) Workshops tenutosi a Seoul; Korea) [10.1109/ICCVW.2019.00152].
File allegati a questo prodotto
File Dimensione Formato  
Amerini_Postprint_Deepfake-Video_2019.pdf

accesso aperto

Note: https://ieeexplore.ieee.org/document/9022558
Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 163.85 kB
Formato Adobe PDF
163.85 kB Adobe PDF
Amerini_Deepfake-Video_2019.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 127.02 kB
Formato Adobe PDF
127.02 kB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1326326
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 265
  • ???jsp.display-item.citation.isi??? 151
social impact