Researchers present how straightforward it’s to defeat AI watermarks

watermark-like image

Enlarge (credit score: James Marshall/Getty Photos)

Soheil Feizi considers himself an optimistic particular person. However the College of Maryland pc science professor is blunt when he sums up the present state of watermarking AI pictures. “We don’t have any dependable watermarking at this level,” he says. “We broke all of them.”

For one of many two sorts of AI watermarking he examined for a brand new research—“low perturbation” watermarks, that are invisible to the bare eye—he’s much more direct: “There’s no hope.”

Learn 13 remaining paragraphs | Feedback

Leave a Reply

Your email address will not be published. Required fields are marked *