Real-time deepfakes can be beaten by a sideways glance

Real-time deepfake videos, heralded as the bringers of a new age of internet uncertainty, appear to have a fundamental flaw: They can't handle side profiles. That's the conclusion drawn in a report [PDF] from Metaphysic.ai, which specializes in 3D avatars, deepfake technology and rendering 3D images from 2D photographs. In tests it conducted using popular real-time deepfake app DeepFaceLive, a hard turn to the side made it readily apparent that the person on screen wasn't who they appeared to be. Multiple models were used in the test - several from deepfake communities and models included in DeepFaceLive - but a a 90-degree view of the face caused flickering and distortion as the Facial Alignment Network used to estimate poses struggled to figure out what it was seeing. "Most 2D-based facial alignments algorithms assign only 50-60 percent of the number of landmarks from a front-on face view to a profile view," said Metaphysic.ai contributor Martin Anderson, who wrote the study's blog post.