Certifying LLM Safety against Adversarial Prompting.

Aounon Kumar Chirag Agarwal Suraj Srinivas Soheil Feizi Hima Lakkaraju

Published in: CoRR (2023)

Keyphrases

multi agent
neural network
training data
nuclear power plant
real time
databases
social networks
metadata
image processing
learning environment
medical images
safety critical
coal mining
civil aviation