This is a problem in this day and age where (mis)information can spread very quickly, which is why Adobe has announced that as part of their research, they have teamed up with researchers at UC Berkeley where they will be training AI to help detect facial manipulation in images that were edited using its Photoshop software.
According to Adobe, “By training a Convolutional Neural Network (CNN), a form of deep learning, the research project is able to recognize altered images of faces. The researchers created an extensive training set of images by scripting Photoshop to use Face Aware Liquify on thousands of pictures scraped from the Internet.”
Adobe researcher Richard Zhang adds, “The idea of a magic universal ‘undo’ button to revert image edits is still far from reality. 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.”