Adobe Research and UC Berkeley Teach AI to Spot Facial Manipulations

Adobe Research and UC Berkeley Teach AI to Spot Facial Manipulations

Adobe presented its new research in collaboration with scientists from UC Berkeley that focuses on using machine learning to automatically detect when images of faces have been manipulated.

Adobe presented its new research in collaboration with scientists from UC Berkeley that focuses on using machine learning to automatically detect when images of faces have been manipulated. The team states that the algorithm can spot up to 99 percent of edited faces.

“While we are proud of the impact that Photoshop and Adobe’s other creative tools have made on the world, we also recognize the ethical implications of our technology,” states the team. “Fake content is a serious and increasingly pressing issue.”

The research is said to be specifically designed to spot edits made using Photoshop’s Liquify tool, which can adjust the shape of faces and alter facial expressions. “The feature’s effects can be delicate which made it an intriguing test case for detecting both drastic and subtle alterations to faces,” states the company.

The team trained a neural network on using a database of paired faces, containing images both before and after they’d been edited using Liquify. The new system event suggests how to restore a photo to its original version, though the results here are not perfect.

“The idea of a magic universal ‘undo’ button to revert image edits is still far from reality,” Adobe researcher Richard Zhang said. “But we live in a world where it’s becoming harder to trust the digital information we consume, and I look forward to further exploring this area of research.”

You can learn more about the project here.

Join discussion

Comments 0

    You might also like

    We need your consent

    We use cookies on this website to make your browsing experience better. By using the site you agree to our use of cookies.Learn more