Five things privacy experts know about AI

by p4bl0on 1/14/25, 10:09 AMwith 1 comments
by Terr_on 1/14/25, 10:22 AM

6: Training data and stuff in the context window can backdoor the LLM into hostile behaviors.

https://promptarmor.substack.com/p/data-exfiltration-from-sl...