With today's technologies, the possibility to generate highly realistic visual fakes is within everyone's reach, leading to major threats in terms of misinformation and data trustworthiness. This holds in particular for synthetically generated faces, which are able to deceive even the most experienced observers, and can be exploited to create fake digital identities with synthetic facial attributes, to be used on social networks and online services. In response to this threat, researchers have employed artificial intelligence to detect synthetic images by analysing patterns and artifacts introduced by the generative models. However, most online images are subject to repeated sharing operations by social media platforms. Said platforms process uploaded images by applying operations (like compression) that progressively degrade those useful forensic traces, compromising the effectiveness of the developed detectors. To solve the synthetic-vs-real problem "in the wild", more realistic image databases are needed to train specialised detectors. In this work, we present TrueFace, a first dataset of socialmedia-processed real and synthetic faces, obtained by the successful StyleGAN generative models, and shared on Facebook, Twitter and Telegram. The dataset is used to validate a ResNet-based image classification model addressing the discrimination of synthetic-vs-real faces in both presocial and post-social scenarios. The results demonstrate that even detectors with extremely high performance on non-shared images struggle to retain their accuracy on images from social media, while fine-tuning with shared images strongly mitigates such performance issues.

TrueFace: a Dataset for the Detection of Synthetic Face Images from Social Networks / Boato, G.; Pasquini, C.; Stefani, A. L.; Verde, S.; Miorandi, D.. - (2022), pp. 1-7. (Intervento presentato al convegno International Joint Conference on Biometrics tenutosi a Abu Dhabi, United Arab Emirates nel 10-13 october 2022) [10.1109/IJCB54206.2022.10007988].

TrueFace: a Dataset for the Detection of Synthetic Face Images from Social Networks

Boato G.;Stefani A. L.;Verde S.;Miorandi D.
2022-01-01

Abstract

With today's technologies, the possibility to generate highly realistic visual fakes is within everyone's reach, leading to major threats in terms of misinformation and data trustworthiness. This holds in particular for synthetically generated faces, which are able to deceive even the most experienced observers, and can be exploited to create fake digital identities with synthetic facial attributes, to be used on social networks and online services. In response to this threat, researchers have employed artificial intelligence to detect synthetic images by analysing patterns and artifacts introduced by the generative models. However, most online images are subject to repeated sharing operations by social media platforms. Said platforms process uploaded images by applying operations (like compression) that progressively degrade those useful forensic traces, compromising the effectiveness of the developed detectors. To solve the synthetic-vs-real problem "in the wild", more realistic image databases are needed to train specialised detectors. In this work, we present TrueFace, a first dataset of socialmedia-processed real and synthetic faces, obtained by the successful StyleGAN generative models, and shared on Facebook, Twitter and Telegram. The dataset is used to validate a ResNet-based image classification model addressing the discrimination of synthetic-vs-real faces in both presocial and post-social scenarios. The results demonstrate that even detectors with extremely high performance on non-shared images struggle to retain their accuracy on images from social media, while fine-tuning with shared images strongly mitigates such performance issues.
2022
Proceeding of International Joint Conference on Biometrics 2022
Piscataway, NJ USA
IEEE
978-1-6654-6394-2
Boato, G.; Pasquini, C.; Stefani, A. L.; Verde, S.; Miorandi, D.
TrueFace: a Dataset for the Detection of Synthetic Face Images from Social Networks / Boato, G.; Pasquini, C.; Stefani, A. L.; Verde, S.; Miorandi, D.. - (2022), pp. 1-7. (Intervento presentato al convegno International Joint Conference on Biometrics tenutosi a Abu Dhabi, United Arab Emirates nel 10-13 october 2022) [10.1109/IJCB54206.2022.10007988].
File in questo prodotto:
File Dimensione Formato  
2022_IJCB_TrueFace.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 358.89 kB
Formato Adobe PDF
358.89 kB Adobe PDF   Visualizza/Apri

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/11572/373077
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 2
social impact