This paper focuses on jailbreaking attacks against large language models
(LLMs), eliciting them to generate objectionable content in response to harmful
user queries. Unlike previous LLM-jailbreaks that directly orient to LLMs, our
approach begins by constructing a multimodal large language model (MLLM)
through the incorporation of a visual module into the target LLM. Subsequently,
we conduct an efficient MLLM-jailbreak to generate jailbreaking embeddings
embJS. Finally, we convert the embJS into text space to facilitate the
jailbreaking of the target LLM. Compared to direct LLM-jailbreaking, our
approach is more efficient, as MLLMs are more vulnerable to jailbreaking than
pure LLM. Additionally, to improve the attack success rate (ASR) of
jailbreaking, we propose an image-text semantic matching scheme to identify a
suitable initial input. Extensive experiments demonstrate that our approach
surpasses current state-of-the-art methods in terms of both efficiency and
effectiveness. Moreover, our approach exhibits superior cross-class
jailbreaking capabilities.

该研究聚焦于针对大型语言模型的越狱攻击，以激发其对有害用户查询的回应中生成令人不悦内容。通过将视觉模块融入目标语言模型，构建一个多模态大型语言模型（MLLM），我们使用高效的 MLLM 越狱方法生成越狱嵌入 embJS，并将其转换为文本空间以促进对目标语言模型的越狱。与直接越狱语言模型相比，我们的方法更加高效，因为 MLLM 比纯语言模型更容易越狱。此外，为提高越狱成功率，我们提出了一种图像 - 文本语义匹配方案以识别适当的初始输入。广泛的实验证明，我们的方法在效率和有效性方面超越了当前最先进的方法。此外，我们的方法具有优越的跨类别越狱能力。