Purple-teaming LLMs with Adversarial Defender Training.

Jingyan Zhou Kun Li Junan Li Jiawen Kang Minda Hu Xixin Wu Helen Meng

Published in: CoRR (2024)

Keyphrases

supervised learning
engineering design
training process
training examples
test set
serious games
training phase
multiscale
multi agent
training set
online learning
feed forward neural networks