Why Social Media Provenance Is More Important Than Ever In An AI-Falsified World

Early applications of deep learning to imagery and video focused primarily on cataloging that content, identifying the objects, activities, locations and text within. As neural algorithms have improved and new techniques developed, there has been an increasing focus on using deep learning approaches to actually generate completely new visual content autonomously. The cost of such AI generated synthetic content is dropping rapidly to the point that in the very near future you'll likely be able to generate it on your smartphone with a click of a button. These images and videos are a far cry from the ham-handed Photoshop jobs of yesteryear, with some appearing nearly flawless even to a trained eye. At the same time, we've taught society that "seeing is believing" and to put far more trust in the visual material we see online – an image might be miscaptioned, but the picture itself is likely real.