Nightshade: University of Chicago's attempt at poisoning AI art generators | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Nightshade: University of Chicago's attempt at poisoning AI art generators (arstechnica.com)
		3 points by Phileosopher on Oct 26, 2023 \| hide \| past \| favorite \| 2 comments

ClassyJacket on Oct 26, 2023 [–]

I wish I was smart enough to understand how things like this work.

thghtihadanacct on Oct 26, 2023 | [–]

a human built language model machine intended to recreate human expressions and interpretations is easily confounded by intentional human subterfuge until some other human builds in a lie detector

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact