Skip to main content ↑ ↓
Topic: Researchers Tested AI Watermarks—and Broke All of Them (Read 33 times) previous topic - next topic

Researchers Tested AI Watermarks—and Broke All of Them

Researchers Tested AI Watermarks—and Broke All of Them

[html]In a new paper out this week, a group from the University of Maryland found it's too easy to evade current methods of watermarking—and even to add fake watermarks to real images.[/html]

Source: Researchers Tested AI Watermarks—and Broke All of Them (http://ht**://www.wired.c**/story/artificial-intelligence-watermarking-issues/)