eduzhai > Applied Sciences > Engineering >

The eyes know it FakeET -- An Eye-tracking Database to Understand Deepfake Perception

  • Save

... pages left unread,continue reading

Document pages: 9 pages

Abstract: We present textbf{FakeET}-- an eye-tracking database to understand humanvisual perception of emph{deepfake} videos. Given that the principal purposeof deepfakes is to deceive human observers, FakeET is designed to understandand evaluate the ease with which viewers can detect synthetic video artifacts.FakeET contains viewing patterns compiled from 40 users via the emph{Tobii}desktop eye-tracker for 811 videos from the textit{Google Deepfake} dataset,with a minimum of two viewings per video. Additionally, EEG responses acquiredvia the emph{Emotiv} sensor are also available. The compiled data confirms (a)distinct eye movement characteristics for emph{real} vs emph{fake} videos;(b) utility of the eye-track saliency maps for spatial forgery localization anddetection, and (c) Error Related Negativity (ERN) triggers in the EEGresponses, and the ability of the emph{raw} EEG signal to distinguish between emph{real} and emph{fake} videos.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×