QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912394042671104 |
|---|---|
| author | Zou, Qingsong Xiao, Jingyu Li, Qing Yan, Zhi Wang, Yuhang Xu, Li Wang, Wenxuan Gao, Kuofeng Li, Ruoyu Jiang, Yong |
| author_facet | Zou, Qingsong Xiao, Jingyu Li, Qing Yan, Zhi Wang, Yuhang Xu, Li Wang, Wenxuan Gao, Kuofeng Li, Ruoyu Jiang, Yong |
| contents | 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://github.com/horizonsinzqs/QueryAttack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09723 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language Zou, Qingsong Xiao, Jingyu Li, Qing Yan, Zhi Wang, Yuhang Xu, Li Wang, Wenxuan Gao, Kuofeng Li, Ruoyu Jiang, Yong Cryptography and Security Artificial Intelligence Computation and Language 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://github.com/horizonsinzqs/QueryAttack. |
| title | QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language |
| topic | Cryptography and Security Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2502.09723 |