NTR Webinar: Deepfakes Detection: Humans vs. Machines

NTR organizes and hosts scientific webinars on neural networks and invites speakers from all over the world to present their recent work at the webinars.

On October 19 Pavel Korshunov, Idiap Research Institute, Martigny, Switzerland, led a technical Zoom webinar on Deepfakes Detection: Humans vs. Machines. 

About the webinar: 

Practically anyone can now generate a realistic looking deepfake video. Many methods to detect deepfakes were recently proposed by the research community. However, it is still unclear how realistic deepfake videos are for an average person and whether the algorithms are significantly better than humans at detecting them. 

In this talk, we compared the results of a subjective study (60 naive subjects) and two deepfake detection algorithms on how hard it is for humans and machines to see if a video is a deepfake or not. 

Webinar presentation.

Moderator and contact: NTR CEO Nick Mikhailovsky: nickm@ntrlab.com.

Leave a Reply

Your email address will not be published. Required fields are marked *