Researchers Tested AI Watermarks—and Broke All of Them | WIRED
jsdz, Watermarking at first sounds like a noble and promising solution
Does it? Watermarking typically aims to be difficult to detect and hard to remove. To me it sounds more like the steganographic equivalent of malware.
phonyphanty, How so? Personally I don’t see AI watermarks as having the same adverse effect as malware.
Add comment