Recently, Large Language Models (LLMs) have garnered significant attention
for their exceptional natural language processing capabilities. However,
concerns about their trustworthiness remain unresolved, particularly in
addressing "jailbreaking" attacks on aligned LLMs. Previous research
predominantly relies on scenarios with white-box LLMs or specific and fixed
prompt templates, which are often impractical and lack broad applicability. In
this paper, we introduce a straightforward and novel method, named
ObscurePrompt, for jailbreaking LLMs, inspired by the observed fragile
alignments in Out-of-Distribution (OOD) data. Specifically, we first formulate
the decision boundary in the jailbreaking process and then explore how obscure
text affects LLM's ethical decision boundary. ObscurePrompt starts with
constructing a base prompt that integrates well-known jailbreaking techniques.
Powerful LLMs are then utilized to obscure the original prompt through
iterative transformations, aiming to bolster the attack's robustness.
Comprehensive experiments show that our approach substantially improves upon
previous methods in terms of attack effectiveness, maintaining efficacy against
two prevalent defense mechanisms. We believe that our work can offer fresh
insights for future research on enhancing LLM alignment.

通过采用 ObscurePrompt 方法，从模糊的文本入手，并利用强大的 LLM 进行迭代转换，增强攻击的稳健性，从而提高对 LLM 的破解效果，并改进先前的方法，以增强 LLM 的对齐性能。