They're known as deepfakes – photos or videos that have been very convincingly manipulated to depict people saying or doing things that they never actually said or did. They're potentially quite the problem, so an experimental new deep neural network has been designed to spot them.
It is now possible to take a talking-head style video, and add, delete or edit the speaker's words as simply as you'd edit text in a word processor. A new deepfake algorithm can process the audio and video into a new file in which the speaker says more or less whatever you want them to.
Using the latest trend in artificial intelligence – adversarial learning – Samsung has demonstrated that it can take a single image of a person and turn it into a talking head. And if watching the Mona Lisa come to life doesn't send chills down your spine, you need to check your pulse.