Login / Signup
AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs.
Zeyi Liao
Huan Sun
Published in:
CoRR (2024)
Keyphrases
</>
generative model
discriminative learning
prior knowledge
learning algorithm
boltzmann machine
learning process
probabilistic model
hidden variables
learned models
supervised learning
image processing
reinforcement learning
em algorithm
topic models
posterior probability
feature representations