Despite the success of DPM in practice, the mechanism behind it remains to be explored.

We adopt a multi-armed bandit framework for this process, enhancing prompt selection based on the returns from online trajectories.

Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, which the current collection of benchmarks and evaluation techniques do not adequately address.