[foerbert]

That bit you quoted seems to be actually correct. It does not mention visual derivatives at all.

That said I think your statement is a bit too strong, but generally true. A hash collision is not going to inherently be visually confusing. However you claim that it is impossible for an image to be both visually confusing and a hash collision, which seems unlikely. The real question is going to be how much more effort it takes to do both.

[zepto]

I didn’t claim it was impossible, just that hash collisions won’t match both.

Also, the information needed to create a full match simply is not available.

[foerbert]

Are those not the same statement?

Unless you're relying on it being computationally infeasible, but I'm not sure we know enough to consider that true at this point. Usually when we make statements on those grounds we do so with substantial proof. I don't think we know enough to do so here. I'm not even sure how feasible it is when you throw DL into the mix.

[zepto]

From the docs: “as an additional safeguard, the visual derivatives themselves are matched to the known CSAM database by a second, inde- pendent perceptual hash. This independent hash is chosen to reject the unlikely possi- bility that the match threshold was exceeded due to non-CSAM images that were ad- versarially perturbed to cause false NeuralHash matches against the on-device en- crypted CSAM database.”

[zepto]

> Are those not the same statement?

No.