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/hpvNxUl
via IFTTT
Comments
Post a Comment