▲ 41 ▼ This new data poisoning tool lets artists fight back against generative AI | MIT Technology Review (www.technologyreview.com) submitted 2 years ago by Masimatutu@mander.xyz to c/technology@lemmy.ml 13 comments fedilink hide all child comments
[–] stoy@lemmy.zip 32 points 2 years ago (1 child) This is the same article I have read before, and it covers technology that doesn't work in reality. The inventors need to read up on a new fringe technology called "anti aliasing", which quickly and easily removes the protection. permalink fedilink source hideshow 2 child comments replies: [–] BetaDoggo_@lemmy.world 4 points 2 years ago That isn't neccesarily true, though for now there's no way to tell since they've yet to release their code. If the timeline is anything like their last paper it will be out around a month after publication, which will be Nov 20th. There have been similar papers for confusing image classification models, not sure how successful they've been IRL. permalink fedilink source parent
[–] BetaDoggo_@lemmy.world 4 points 2 years ago That isn't neccesarily true, though for now there's no way to tell since they've yet to release their code. If the timeline is anything like their last paper it will be out around a month after publication, which will be Nov 20th. There have been similar papers for confusing image classification models, not sure how successful they've been IRL. permalink fedilink source parent