Certainly detecting the source of a digital video it is a crucial task to be tackled by the image forensic scientific community; in fact, knowing the brand and model of the device used for the video acquisition could be very useful to focus investigations in a specific direction. Nowadays, videos are mostly acquired through a smartphone and then shared on Social Networks (SNs). On such a basis, this paper proposes an analysis for the source identification of a video uploaded on social networks, specifically, Twitter and Facebook. Furthermore, the paper evaluates different methods to build a reliable fingerprint and also introduces a novel method to generate a composite fingerprint by resorting to the use of PRNU noise. A tool to examine videos, oriented to forensic analysts, is also presented. Experimental results carried out on various videos, firstly uploaded and then downloaded from Facebook or Twitter, witness that the identification is still possible and under which conditions. © 2017

Dealing with video source identification in social networks / Amerini, I; Caldelli, R; Del Mastio, A; Di Fuccia, A; Molinari, C; Rizzo, Ap. - In: SIGNAL PROCESSING-IMAGE COMMUNICATION. - ISSN 0923-5965. - 57:(2017), pp. 1-7. [10.1016/j.image.2017.04.009]

Dealing with video source identification in social networks

Amerini I
;
2017

Abstract

Certainly detecting the source of a digital video it is a crucial task to be tackled by the image forensic scientific community; in fact, knowing the brand and model of the device used for the video acquisition could be very useful to focus investigations in a specific direction. Nowadays, videos are mostly acquired through a smartphone and then shared on Social Networks (SNs). On such a basis, this paper proposes an analysis for the source identification of a video uploaded on social networks, specifically, Twitter and Facebook. Furthermore, the paper evaluates different methods to build a reliable fingerprint and also introduces a novel method to generate a composite fingerprint by resorting to the use of PRNU noise. A tool to examine videos, oriented to forensic analysts, is also presented. Experimental results carried out on various videos, firstly uploaded and then downloaded from Facebook or Twitter, witness that the identification is still possible and under which conditions. © 2017
2017
Algorithms; Cameras; Image tampering
01 Pubblicazione su rivista::01a Articolo in rivista
Dealing with video source identification in social networks / Amerini, I; Caldelli, R; Del Mastio, A; Di Fuccia, A; Molinari, C; Rizzo, Ap. - In: SIGNAL PROCESSING-IMAGE COMMUNICATION. - ISSN 0923-5965. - 57:(2017), pp. 1-7. [10.1016/j.image.2017.04.009]
File allegati a questo prodotto
File Dimensione Formato  
Amerini_Dealing-with-video_2017.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.83 MB
Formato Adobe PDF
1.83 MB Adobe PDF   Contatta l'autore
Amerini_preprint_Dealing-with-video_2017.pdf

accesso aperto

Note: http://dx.doi.org/10.1016/j.image.2017.04.009
Tipologia: Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.25 MB
Formato Adobe PDF
1.25 MB Adobe PDF

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/11573/1325042
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 31
  • ???jsp.display-item.citation.isi??? 26
social impact