The Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology (MIT CSAIL) has developed PhotoGuard technology, which will help protect images from malicious editing by artificial intelligence. This is reported by Engadget.

PhotoGuard works by altering individual pixels in an image in such a way that they disrupt the AI’s ability to understand what the image is. Changes are invisible to the human eye, but easily read by machines. In fact, this method masks the image in the “eyes” of the AI, so it does not understand what exactly it is “looking at”.

Any edits that AI tries to make to such protected images will produce an unrealistic result.

By the way, recently it became known that the startup Stability AI launches the Stable Doodle service, which turns sketches into images. The service uses the latest Stable Diffusion model to analyze the contours of a sketch and create a “visually pleasing” artistic image of it. It is available through the ClipDrop platform.