A small number of samples can poison LLMs of any size:
anthropic.com/research/small-s…

"In a joint study with the UK AI Security Institute and the Alan Turing Institute, we found that as few as 250 malicious documents can produce a "#backdoor" vulnerability in a large language model—regardless of model size or training data volume."

Size does not matter: the #LLM edition. 😜

#AI #Claude #backdoors #malware #Anthropic

A small number of samples can poison LLMs of any size

Anthropic research on data-poisoning attacks in large language models

^{www.anthropic.com}