News for hackers. Stuff that matters.

A comment on Researchers Tested AI Watermarks–and Broke All of Them. Parent comment

Re:Researchers Tested AI Watermarks–and Broke All of Them by AnthonyMouse on Saturday October 07, 2023 @01:58PM (#37803987)
The value isn't that the users are going to do it under normal circumstances. They would see the edited photo. You'd only care about the signature if its provenance came into question.

You could also handle cropping and omissions by having the original device sign the picture as a grid of individual tiles. Then you could omit some and still prove that the others are original.

[ Parent | on HN ]
Re:Researchers Tested AI Watermarks–and Broke All of Them by danShumway on Saturday October 07, 2023 @03:59PM (#37805033)
I'm still skeptical that this would end up working well in practice, but I do want to say:

> You could also handle cropping and omissions by having the original device sign the picture as a grid of individual tiles.

is a pretty good idea, I like that quite a lot. Not saying it means I'm on board with signatures overall (I mean, we're still in agreement that this would require locking down devices to at least some degree) but I do think that's an elegant solution for the cropping/censoring part of it.

[ Parent | on HN ]