A study finds that as few as 250 malicious documents can produce a "backdoor" vulnerability in an LLM, regardless of model size or training data volume (Anthropic)

Anthropic:
A study finds that as few as 250 malicious documents can produce a “backdoor” vulnerability in an LLM, regardless of model size or training data volume  —  Read the paper … Large language models like Claude are pretrained on enormous amounts of public text from across the internet …



from Techmeme https://ift.tt/SXi2MDn

Comments

Popular posts from this blog

Guilherme Rambo, who has published scoops about unreleased Apple products by examining beta software, says Apple locked his dev account with no stated reason (Buster Hein/Cult of Mac)

Barcelona nights

Upward and onward