Konferenzbeitrag
A Generalizable Deepfake Detector based on Neural Conditional Distribution Modelling
Vorschaubild nicht verfügbar
Volltext URI
Dokumententyp
Text/Conference Paper
Zusatzinformation
Datum
2020
Autor:innen
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Verlag
Gesellschaft für Informatik e.V.
Zusammenfassung
Photo- and video-realistic generation techniques have become a reality following the advent
of deep neural networks. Consequently, there are immense concerns regarding the difficulty in
differentiating what content is real from what is synthetic. An example of video-realistic generation
techniques is the infamous Deepfakes, which exploit the main modality by which humans identify
each other. Deepfakes are a category of synthetic face generation methods and are commonly based
on generative adversarial networks. In this article, we propose a novel two-step synthetic face image
detection method in which general-purpose features are extracted in a first step, trivializing the
task of detecting synthetic images. The anomaly detector predicts the conditional probabilities for
observing every individual pixel in the image and is trained on pristine data only. The extracted
anomaly features demonstrate true generalization capacity across widely different unknown synthesis
methods while showing a minimal loss in performance with regard to the detection of known
synthetic samples.