QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao
Abstract
Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety alignment are developed for defense, prior researches reveal the possibility of bypassing such defenses through well-designed jailbreak attacks. In this paper, we propose QueryAttack, a novel framework to examine the generalizability of safety alignment. By treating LLMs as knowledge databases, we translate malicious queries in natural language into structured non-natural query language to bypass the safety alignment mechanisms of LLMs. We conduct extensive experiments on mainstream LLMs, and the results show that QueryAttack not only can achieve high attack success rates (ASRs), but also can jailbreak various defense methods. Furthermore, we tailor a defense method against QueryAttack, which can reduce ASR by up to 64% on GPT-4-1106. Our code is available at https://anonymous.4open.science/r/QueryAttack-334B.
BibTeX
@inproceedings{zou-etal-2025-queryattack,
title = "{Q}uery{A}ttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language",
author = "Zou, Qingsong and
Xiao, Jingyu and
Li, Qing and
Yan, Zhi and
Wang, Yuhang and
Xu, Li and
Wang, Wenxuan and
Gao, Kuofeng and
Li, Ruoyu and
Jiang, Yong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.298/",
doi = "10.18653/v1/2025.findings-acl.298",
pages = "5725--5741",
ISBN = "979-8-89176-256-5"
}