@inproceedings{zhao-etal-2025-sql,
title = "{SQL} Injection Jailbreak: A Structural Disaster of Large Language Models",
author = "Zhao, Jiawei and
Chen, Kejiang and
Zhang, Weiming and
Yu, Nenghai",
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.358/",
doi = "10.18653/v1/2025.findings-acl.358",
pages = "6871--6891",
ISBN = "979-8-89176-256-5",
abstract = "Large Language Models (LLMs) are susceptible to jailbreak attacks that can induce them to generate harmful content.Previous jailbreak methods primarily exploited the internal properties or capabilities of LLMs, such as optimization-based jailbreak methods and methods that leveraged the model{'}s context-learning abilities. In this paper, we introduce a novel jailbreak method, SQL Injection Jailbreak (SIJ), which targets the external properties of LLMs, specifically, the way LLMs construct input prompts. By injecting jailbreak information into user prompts, SIJ successfully induces the model to output harmful content. For open-source models, SIJ achieves near 100{\%} attack success rates on five well-known LLMs on the AdvBench and HEx-PHI, while incurring lower time costs compared to previous methods. For closed-source models, SIJ achieves an average attack success rate over 85{\%} across five models in the GPT and Doubao series. Additionally, SIJ exposes a new vulnerability in LLMs that urgently requires mitigation. To address this, we propose a simple adaptive defense method called Self-Reminder-Key to counter SIJ and demonstrate its effectiveness through experimental results. Our code is available at https://github.com/weiyezhimeng/SQL-Injection-Jailbreak."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2025-sql">
<titleInfo>
<title>SQL Injection Jailbreak: A Structural Disaster of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kejiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nenghai</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) are susceptible to jailbreak attacks that can induce them to generate harmful content.Previous jailbreak methods primarily exploited the internal properties or capabilities of LLMs, such as optimization-based jailbreak methods and methods that leveraged the model’s context-learning abilities. In this paper, we introduce a novel jailbreak method, SQL Injection Jailbreak (SIJ), which targets the external properties of LLMs, specifically, the way LLMs construct input prompts. By injecting jailbreak information into user prompts, SIJ successfully induces the model to output harmful content. For open-source models, SIJ achieves near 100% attack success rates on five well-known LLMs on the AdvBench and HEx-PHI, while incurring lower time costs compared to previous methods. For closed-source models, SIJ achieves an average attack success rate over 85% across five models in the GPT and Doubao series. Additionally, SIJ exposes a new vulnerability in LLMs that urgently requires mitigation. To address this, we propose a simple adaptive defense method called Self-Reminder-Key to counter SIJ and demonstrate its effectiveness through experimental results. Our code is available at https://github.com/weiyezhimeng/SQL-Injection-Jailbreak.</abstract>
<identifier type="citekey">zhao-etal-2025-sql</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.358</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.358/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>6871</start>
<end>6891</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SQL Injection Jailbreak: A Structural Disaster of Large Language Models
%A Zhao, Jiawei
%A Chen, Kejiang
%A Zhang, Weiming
%A Yu, Nenghai
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhao-etal-2025-sql
%X Large Language Models (LLMs) are susceptible to jailbreak attacks that can induce them to generate harmful content.Previous jailbreak methods primarily exploited the internal properties or capabilities of LLMs, such as optimization-based jailbreak methods and methods that leveraged the model’s context-learning abilities. In this paper, we introduce a novel jailbreak method, SQL Injection Jailbreak (SIJ), which targets the external properties of LLMs, specifically, the way LLMs construct input prompts. By injecting jailbreak information into user prompts, SIJ successfully induces the model to output harmful content. For open-source models, SIJ achieves near 100% attack success rates on five well-known LLMs on the AdvBench and HEx-PHI, while incurring lower time costs compared to previous methods. For closed-source models, SIJ achieves an average attack success rate over 85% across five models in the GPT and Doubao series. Additionally, SIJ exposes a new vulnerability in LLMs that urgently requires mitigation. To address this, we propose a simple adaptive defense method called Self-Reminder-Key to counter SIJ and demonstrate its effectiveness through experimental results. Our code is available at https://github.com/weiyezhimeng/SQL-Injection-Jailbreak.
%R 10.18653/v1/2025.findings-acl.358
%U https://aclanthology.org/2025.findings-acl.358/
%U https://doi.org/10.18653/v1/2025.findings-acl.358
%P 6871-6891
Markdown (Informal)
[SQL Injection Jailbreak: A Structural Disaster of Large Language Models](https://aclanthology.org/2025.findings-acl.358/) (Zhao et al., Findings 2025)
ACL