deepfake detector tagged posts

Team develops a new Deepfake Detector designed to be Less Biased

Study: New deepfake detector designed to be less biased
Deepfake detection algorithms often perform differently across races and genders, including a higher false positive rate on Black men than on white women. New algorithms developed at the University at Buffalo are designed to reduce such gaps. Credit: Siwei Lyu

University at Buffalo computer scientist and deepfake expert Siwei Lyu created a photo collage out of the hundreds of faces that his detection algorithms had incorrectly classified as fake—and the new composition clearly had a predominantly) darker skin tone.

“A detection algorithm’s accuracy should be statistically independent from factors like race,” Lyu says, “but obviously many existing algorithms, including our own, inherit a bias.”

Lyu, Ph.D...

Read More