companies would stumble all over themselves to figure out how to get it to stop doing that before going live. source: they already are. see bing image generator appending “ethnically ambiguous” to every prompt it receives
Comment on Data poisoning: how artists are sabotaging AI to take revenge on image generators
HejMedDig@feddit.dk 6 months ago
Let’s see how long before someone figures out how to poison, so it returns NSFW Images
AVincentInSpace@pawb.social 6 months ago
General_Effort@lemmy.world 6 months ago
It can only target open source, so it wouldn’t bother corpos at all. The people behind this object to not everything being owned and controlled. That’s the whole point.
HejMedDig@feddit.dk 6 months ago
The Nightshade poisoning attack claims that it can corrupt a Stable Diffusion in less than 100 samples. Probably not to NSFW level. How easy it is to manufacture those 100 samples is not mentioned in the abstract
AVincentInSpace@pawb.social 6 months ago
yeah the operative word in that sentence is “claims”
I’d love nothing more than to be wrong, but after seeing how quickly Glaze got defeated (not only did it make the images nauseating for a human to look at despite claiming to be invisible, not even 48 hours after launch there was a neural network trained to reverse its effects automatically with like 95% accuracy), suffice to say my hopes aren’t high.
HejMedDig@feddit.dk 6 months ago
You seem to have more knowledge on this than me, I just read the article 🙂
daxnx01@lemmy.world 6 months ago
You can create NSFW ai images already though?
Or did you mean, when poisoned data is used a NSFW image is created instead of the expected image?
HejMedDig@feddit.dk 6 months ago
Definitely the last one!