Detecting ‘deepfake’ videos in the blink of an eye

File 20180816 2924 1sl2vye
’A new form of misinformation is poised to spread through online communities as the 2018 midterm election campaigns heat up. Called “deepfakes” after the pseudonymous online account that popularized the technique – which may have chosen its name because the process uses a technical method called “deep learning” – these fake videos look very realistic.

So far, people have used deepfake videos in pornography and satire to make it appear that famous people are doing things they wouldn’t normally. But it’s almost certain deepfakes will appear during the campaign season, purporting to depict candidates saying things or going places the real candidate wouldn’t.

Because these techniques are so new, people are
having trouble telling the difference between real videos and the deepfake videos. My work, with my colleague Ming-Ching Chang and our Ph.D. student Yuezun Li, has found a way to reliably tell real videos from deepfake videos. It’s not a permanent solution, because technology will improve. But it’s a start, and offers hope that computers will be able to help people tell truth from fiction.…

When a deepfake algorithm is trained on face images of a person, it’s dependent on the photos that are available on the internet that can be used as training data. Even for people who are photographed often, few images are available online showing their eyes closed. Not only are photos like that rare – because people’s eyes are open most of the time – but photographers don’t usually publish images where the main subjects’ eyes are shut.

Without training images of people blinking, deepfake algorithms are less likely to create faces that blink normally. When we calculate the overall rate of blinking, and compares that with the natural range, we found that characters in deepfake videos blink a lot less frequent in comparison with real people. Our research uses machine learning to examine eye opening and closing in videos…’

Via The Conversation