Can't pop-lock or Lindy Hop to save your life? Don't worry -- AI could soon make it look like you're a dance superstar. UC Berkeley researchers have developed a deep learning system that translates dance moves from a source video to less-than-experienced subjects. One algorithm creates a virtual skeleton to map poses, while two more algorithms square off against each other to both create the full picture and create a more realistic face for subjects as their virtual bodies twirl around. You do need the test subject to move around for a short while to get reference material, but the result is realistic enough to give an amateur the deftness of a ballet dancer.
As fake videos generated by AI continue to become more convincing, what was once a tool to share laughs on the internet has grown into a worrying sector of digital media. Whether it's a viral video of "Tom Cruise" doing a magic trick or "Facebook's Mark Zuckerberg" boasting about having "total control of billions of people's stolen data," deepfake videos have the capacity to cause real harm to people who fall for their deception. A Pennsylvania woman was charged last weekend with allegedly making deepfake videos of girls on a cheerleading team her daughter used to belong to – the videos showed the girls nude, smoking or partying – in an attempt to get them kicked off the team. Graphic artist Chris Ume, the mastermind behind the Tom Cruise TikTok deepfake, told CTV News that when he started making deepfake videos it was just to "have good fun." But now as manipulated media continues to make headlines, his views have changed.
When used in the context of movies and memes, deepfakes can occasionally be a source of entertainment. AI-generated, manipulated photos, videos, or audio files -- could potentially be used to confuse and mislead people. Microsoft, however, has other ideas. On Tuesday, the company announced two new pieces of technology, both of which aim to give readers the necessary tools to filter out what's real and what isn't. The first of these, the Microsoft Video Authenticator, analyses images and videos to give "a percentage chance, or confidence score, that the media is artificially manipulated," per a blog on Microsoft's official site.
TikTok users have been spooked by an uncanny deepfake of actor Tom Cruise that's going viral on the app, with many mistaking him as the real-deal at first glance. Deepfaking is something that people have been both fascinated and terrified by for some time now. The technology allows you to replace the faces of people in existing videos, using machine learning to make the final product look practically real. The technology is becoming so advanced that people are calling for governments to put limitations on deepfaking in order to protect people, with some videos being used for illegal purposes. In the past, TikTok stars Addison Rae and Dixie D'Amelio have responded to people making inappropriate deepfakes of them online, with celebrities and influencers being a prime target.
About a year ago, top deepfake artist Hao Li came to a disturbing realization: Deepfakes, i.e. the technique of human-image synthesis based on artificial intelligence (AI) to create fake content, is rapidly evolving. In fact, Li believes that in as soon as six months, deepfake videos will be completely undetectable. And that's spurring security and privacy concerns as the AI behind the technology becomes commercialized – and gets in the hands of malicious actors. Li, for his part, has seen the positives of the technology as a pioneering computer graphics and vision researcher, particularly for entertainment. He has worked his magic on various high-profile deepfake applications – from leading the charge in putting Paul Walker into Furious 7 after the actor died before the film finished production, to creating the facial-animation technology that Apple now uses in its Animoji feature in the iPhone X.