A small number of samples can poison #LLMs of any size
"Specifically, we demonstrate that by injecting just 250 malicious documents into pretraining data, adversaries can successfully backdoor LLMs ranging from 600M to 13B parameters."
cc @asrg
Post
A small number of samples can poison #LLMs of any size
"Specifically, we demonstrate that by injecting just 250 malicious documents into pretraining data, adversaries can successfully backdoor LLMs ranging from 600M to 13B parameters."
cc @asrg
A space for Bonfire maintainers and contributors to communicate
