“Don’t expect quick fixes in ‘red-teaming’ of AI models. Security was an afterthought”
… tricked a Google system into labeling a piece of malware harmless merely by inserting a line that said “this is safe to use.”
... works as a web developer in Hveragerði, Iceland, and writes about the web, digital publishing, and web/product development
These are his notes
“Don’t expect quick fixes in ‘red-teaming’ of AI models. Security was an afterthought”
… tricked a Google system into labeling a piece of malware harmless merely by inserting a line that said “this is safe to use.”