Researchers have discovered a surprisingly simple way to detectdeepfakevideo calls: ask the suspect to turn sideways.
The trick was shared this week byMetaphysic.ai, a London-based startup behindthe viral Tom Cruise deepfakes.
The company used DeepFaceLive, a popular app for video deepfakes, to transform a volunteer into various celebrities.
Most of the recreations were impressive when they looked straight-ahead.
But once the faces rotated a full 90-degrees, the images became distorted and the spell was broken.
The team believes the defects emerge because the softwareuses fewer reference pointsto estimate lateral views of faces.
This makes thealgorithmunable to guess how it would look.
It’s free, every week, in your inbox.
These weak spots can be strengthened, but it takes a lot of work.
In addition, the profile-view of Seinfeld closely resembled the original actor.
This can leave deepfake models with insufficient training data to generate realistic lateral views.
Metaphysic.ais research emerges amid growing concerns about deepfake video calls.
In June, several European mayors wereduped by a video call from a fake Vitali Klitschko.
Days later, theFBIwarned that scammers were using deepfakesin interviews for fully-remote jobs that offer access to valuable information.
The side-on trick may not have saved all of the victims.
Future 3D landmark systems may produce convincing profile views, while photorealistic CGI models could replace entire heads.
Story byThomas Macaulay
Thomas is the managing editor of TNW.
He leads our coverage of European tech and oversees our talented team of writers.
Away from work, he e(show all)Thomas is the managing editor of TNW.
He leads our coverage of European tech and oversees our talented team of writers.
Away from work, he enjoys playing chess (badly) and the guitar (even worse).
