Comment by minimaxir
3 years ago
> You wouldn't be able to denoise as you'd have to denoise the entire dataset
Doing that requires much less compute than training a large generative image model.
3 years ago
> You wouldn't be able to denoise as you'd have to denoise the entire dataset
Doing that requires much less compute than training a large generative image model.
I guess the idea is that the model trainers are ignorant of this and wouldn't know to preprocess/wouldn't bother?
That's actually quite plausible.
> I guess the idea is that the model trainers are ignorant of this
Maybe they're ignorant of it right up until you announce it, but then they're no longer ignorant of it.
Right, but they aren't necessarily paying attention to this.
I am not trying to belittle foundational model trainers, but a lot goes on in ML land. Even groups can't track every development.
> the entire point is that these are virtually undetectable from typical training set examples
I'll repeat this point for clarity. After going over the paper again, denoising shouldn't affect this attack, it's the ability of plausible images to not be detected by human or AI discriminators (yet)