The detector measures blood flow by analysing how the colour of pixels change as blood flows through the body.can be incredibly convincing. Take our header image for example. While all of those people look real, they were actually generated by an AI. The ability to harness the power of artificial intelligence to fake an entire human down to their voice opens up dangerous avenues for nefarious individuals and groups.
“Most deep learning-based detectors look at raw data to try to find signs of inauthenticity and identify what is wrong with a video. In contrast, FakeCatcher looks for authentic clues in real videos, by assessing what makes us human— subtle ‘blood flow’ in the pixels of a video. When our hearts pump blood, our veins change colour,” Intel explains.
Intel says FakeCatcher has a 96 percent accuracy rate though that depends largely on which dataset is being tested.