MIT team offers PhotoGuard to thwart deepfake AI models

Ireland News News

MIT team offers PhotoGuard to thwart deepfake AI models
Ireland Latest News,Ireland Headlines
  • 📰 TheRegister
  • ⏱ Reading Time:
  • 38 sec. here
  • 2 min. at publisher
  • 📊 Quality Score:
  • News: 19%
  • Publisher: 61%

Maybe one way to protect photos from manipulation by AI software is to slightly perturb the image data to confuse those models A team at MIT have proposed such an approach with code and a paper. It's not entirely foolproof, tho More:

Finally, an AI that can reliably catch and undo Photoshop airbrushing. Who made it? Er, Photoshop maker Adobe

Figure from the MIT PhotoGuard paper outlining how this immunization of data from manipulation basically works – Click to enlarge "When applying the encoder attack, our goal is to map the representation of the original image to the representation of a target image ," the team wrote in their paper."Our diffusion attack, on the other hand, aims to break the diffusion process by manipulating the whole process to generate an image that resembles a given target image ."

"A collaborative approach involving model developers, social media platforms, and policymakers presents a robust defense against unauthorized image manipulation. Working on this pressing issue is of paramount importance today," argued Salman.

We have summarized this news so that you can read it quickly. If you are interested in the news, you can read the full text here. Read more:

TheRegister /  🏆 67. in UK

Ireland Latest News, Ireland Headlines



Render Time: 2025-03-12 21:22:40