But -- bright side! Thinking about deepfakes tends to lead to philosophical head-scratchers. Here's one: Should you worry about your face being grafted into hard-core pornography if deepfakes are bent on sabotaging global power? Deepfakes are video forgeries that make people appear to be doing or saying things they never did.
Deepfakes Are Getting Better, But They're Still Easy to Spot
Disinformation on Steroids: The Threat of Deep Fakes
Deep Video Portraits is the title of a paper submitted for consideration this August at SIGGRAPH; it describes an improved technique for reproducing the motions, facial expressions and speech movements of one person using the face of another. It uses a video of a target person, in this case President Obama, to get a handle on what constitutes the face, eyebrows, corners of the mouth, background and so on, and how they move normally. If you look closely, even the shadows behind the person if present are accurate. The researchers verified the effectiveness of this by comparing video of a person actually saying something on video with what the deep learning network produced using that same video as a source. And naturally there are all kinds of little bugs and artifacts. So for now the hijinks are limited. But as you can see from the comparison with previous attempts at doing this, the science is advancing at a rapid pace.
Forget DeepFakes, Deep Video Portraits are way better (and worse)
Last week, Mona Lisa smiled. A big, wide smile, followed by what appeared to be a laugh and the silent mouthing of words that could only be an answer to the mystery that had beguiled her viewers for centuries. And yes, it could, in theory, be used to animate your Facebook profile photo. Using as little as one source image, the researchers were able to manipulate the facial expressions of people depicted in portraits and photos.
Republish our articles for free, online or in print, under Creative Commons licence. Deepfake videos are hard for untrained eyes to detect because they can be quite realistic. Most deepfakes are made by showing a computer algorithm many images of a person, and then having it use what it saw to generate new face images. At the same time, their voice is synthesized, so it both looks and sounds like the person has said something new. Now, our research can identify the manipulation of a video by looking closely at the pixels of specific frames.