Nested Gloss Makes Large Language Models Lost

Xuan Li, Zhanke Zhou, Jianing Zhu, Jiangchao Yao, Tongliang Liu, Bo Han

Keywords: Trustworthy Machine Learning; Large Language Model

TL;DR: We propose a jailbreak attack method to bypass LLMs' safety protocols by concealing the attack intention with nested instructions.

Abstract:

Large language models (LLMs) have succeeded significantly in various applications but remain susceptible to adversarial jailbreaks that void their safety guardrails.
Previous attempts to exploit these vulnerabilities often rely on high-cost computational extrapolations, which may not be practical or efficient.
In this paper, inspired by the authority influence demonstrated in the Milgram experiment, we present a lightweight method to take advantage of the LLMs' personification capabilities to construct $\textit{a virtual, nested scene}$, allowing it to realize an adaptive way to escape the usage control in a normal scenario.
Empirically, the contents induced by our approach can achieve leading harmfulness rates with previous counterparts and realize a continuous jailbreak in subsequent interactions, which reveals the critical weakness of self-losing on both open-source and closed-source LLMs, $\textit{e.g.}$, Llama-2, Llama-3, GPT-3.5, GPT-4, and GPT-4o.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9192