Some researchers, however, are now fighting back and developing new ways to protect people’s photos and images from AI’s grasp.
The prototype, dubbed PhotoGuard, puts an invisible “immunization” over images that stops AI models from being able to manipulate the picture.
The aim of PhotoGuard is to protect photos that people upload online from “malicious manipulation by AI models,” Salman said.
But he said he hopes that with more engineering efforts, the prototype can be turned into a larger product that can be used to protect images.
While generative AI tools “allow us to do amazing stuff, it comes with huge risks,” Salman said.
Persons:
Eveline, ”, Fröhlich, “ We’ve, Glaze, ” Fröhlich, “, AI’s overreach, Pope dripped, Vincent Van Gogh, they’re, it’s, Ben Zhao, ” Zhao, Zhao’s, Jon Lam, Lam, Jon Lam “, ” Lam, Zhao, ‘, ” Hadi Salman, ” Salman, Salman, Trevor Noah, MIT CSAIL, Noah
Organizations:
CNN, University of Chicago, Massachusetts Institute of Technology, MIT, PhotoGuard
Locations:
Stuttgart, Germany, California