Adobe develops tool to spot digitally manipulated images of faces
From the company that created Photoshop, Adobe is now making tools to help users spot if what they are seeing has been manipulated.
With things like AI and Deepfake videos and more and more people being suscseptible to manipulated content, the need to verify information is now more important than ever.
Which is why the company that created Photoshop, it seems the company is now making the tools to help users spot if an image has been photoshopped.
Adobe Photoshop has been around since the 90's and it has been a milestone in the way we view and create content on the internet. In a blog post, Adobe has said that it's now commited to building technologies to detect edits using AI.
Adobe researchers Richard Zhang and Oliver Wang, along with their UC Berkeley collaborators, Sheng-Yu Wang, Dr. Andrew Owens, and Professor Alexei A. Efros, developed a method for detecting edits to images that were made using Photoshop's Face Aware Liquify feature. While still in its early stages, this collaboration between Adobe Research and UC Berkeley, is a step towards democratizing image forensics, the science of uncovering and analyzing changes to digital images
This new research is part of a broader effort across Adobe to better detect image, video, audio and document manipulations. Past Adobe research focused on image manipulation detection from splicing, cloning, and removal, whereas this effort focuses on the Face Aware Liquify feature in Photoshop because it's popular for adjusting facial features, including making adjustments to 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.
"We started by showing image pairs (an original and an alteration) to people who knew that one of the faces was altered," Oliver says. "For this approach to be useful, it should be able to perform significantly better than the human eye at identifying edited faces."
Those human eyes were able to judge the altered face 53% of the time, a little better than chance. But in a series of experiments, the neural network tool achieved results as high as 99%.
The tool also identified specific areas and methods of facial warping. In the experiment, the tool reverted altered images to its calculation of their original state, with results that impressed even the researchers.
"This is an important step in being able to detect certain types of image editing, and the undo capability works surprisingly well," says head of Adobe Research, Gavin Miller. "Beyond technologies like this, the best defense will be a sophisticated public who know that content can be manipulated - often to delight them, but sometimes to mislead them."