Bypassing the Safety Training of Open-Source LLMs with Priming Attacks

Open Webpage

Jason Vega, Isha Chaudhary, Changming Xu, Gagandeep Singh

Published: 01 Jan 2024, Last Modified: 30 Sept 2024Tiny Papers @ ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0