Furry Technologists

1506 readers

1 users here now

Science, Technology, and pawbs

founded 2 years ago

MODERATORS

Soatok@pawb.social

stefenauris@pawb.social

Researchers Tested AI Watermarks—and Broke All of Them | WIRED (www.wired.com)

submitted 2 years ago by stefenauris@pawb.social to c/tech@pawb.social

2 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] jsdz@lemmy.ml 8 points 2 years ago (1 children)

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.

permalink
fedilink
source
hideshow 2 child comments

[–] phonyphanty@pawb.social 1 points 2 years ago

How so? Personally I don't see AI watermarks as having the same adverse effect as malware.

permalink
fedilink
source
parent