Oct 3, 2023

Vulnerable Watermarks: WIRED Consults Hany Farid on Watermarking Deepfakes

From WIRED

Researchers Tested AI Watermarks—and Broke All of Them

By Kate Knibbs

SOHEIL FEIZI CONSIDERS himself an optimistic person. But the University of Maryland computer science professor is blunt when he sums up the current state of watermarking AI images. “We don’t have any reliable watermarking at this point,” he says. “We broke all of them.”

For one of the two types of AI watermarking he tested for a new study—“low perturbation” watermarks, which are invisible to the naked eye—he’s even more direct: “There’s no hope...”

It’s a solid, straightforward strategy, but it might not be a winning one. This study is not the only work pointing to watermarking’s major shortcomings. “It is well established that watermarking can be vulnerable to attack,” says Hany Farid, a professor at the UC Berkeley School of Information...

Read the full article.

Hany Farid is a professor in the Department of Electrical Engineering & Computer Sciences and the School of Information at UC Berkeley.

Last updated: October 4, 2023