Images that are edited in apps like Photoshop may look convincing to the human eye, but there are many artifacts that can be more easily detected by a computer. For example, the clone tool creates repeated patterns in an image that may be virtually undetectable to the untrained eye, but — to a computer — are clear indications of manipulation. Assembler specifically looks for these common giveaways, as well as signs from more advanced forms of image manipulation, like deepfakes.

According to Jigsaw CEO, Jared Cohen, Assembler is still in its early stages of development, and will only be available to journalists and fact checkers. Other image analysis software — such as FotoForensics — exists, but Assembler seems to be much more advanced. As fake news shows no signs of abating, Assembler could become a key tool for journalists and researchers.

A video call is a great way to connect with friends and family when you can’t physically be together. But even if you’re staring directly at your loved one’s face, there’s still something a little off about the whole process. The way your phone’s screen display and camera lens sync up means you’re never quite able to look your conversational partner squarely in the eye. Until now, that is. Apple is allegedly working on a new feature that subtly adjusts your gaze during video calls, so it appears as if you’re looking into the camera when you’re actually looking at the screen.

The team trained a convolutional neural network (CNN) to spot changes in images made with Photoshop’s Face Away Liquify feature, which was designed to change people’s eyes, mouth and other facial features. When put to the test, the neural network detected altered images up to 99 percent of the time. In comparison, people who saw the same photos only spotted the changes 53 percent of the time. The tool was also able to revert images to what it predicted was their original state.

This isn’t the first time, Adobe has used AI to spot photoshopped images, but this work is specifically targeted at detecting facial manipulation. The company says the work is more pressing than ever. “We live in a world where it’s becoming harder to trust the digital information we consume,” said Adobe researcher Richard Zhang. And when it comes to spotting manipulated images and altered faces, Adobe says this is just the beginning.