When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914552287854592 |
|---|---|
| author | Motlagh, Farzad Nourmohammadzadeh Hajizadeh, Mehrdad Majd, Mehryar Najafi, Pejman Cheng, Feng Meinel, Christoph |
| author_facet | Motlagh, Farzad Nourmohammadzadeh Hajizadeh, Mehrdad Majd, Mehryar Najafi, Pejman Cheng, Feng Meinel, Christoph |
| contents | Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such as SQL. While this paradigm significantly improves usability and accessibility, it introduces new security risks, particularly the amplification of SQL injection vulnerabilities through the prompt-to-SQL translation process. Malicious users can exploit these mechanisms by crafting adversarial prompts that manipulate model behavior and generate unsafe queries. In this work, we propose a multi-layered security framework designed to detect and mitigate LLM-mediated SQL injection attacks. The framework integrates a front-end security shield for prompt sanitization, an advanced threat detection model for behavioral and semantic anomaly identification, and a signature-based control layer for known attack patterns. We evaluate the proposed framework under diverse and realistic attack scenarios, including prompt injection, obfuscated SQL payloads, and context-manipulation attacks. To ensure robustness, we generate and curate a comprehensive benchmark dataset of adversarial prompts and assess performance across a fine-tuned LLM configuration. Experimental results demonstrate that the proposed approach achieves high detection accuracy while maintaining low false-positive rates, significantly improving the secure deployment of LLM-powered database applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10176 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications Motlagh, Farzad Nourmohammadzadeh Hajizadeh, Mehrdad Majd, Mehryar Najafi, Pejman Cheng, Feng Meinel, Christoph Cryptography and Security Artificial Intelligence D.4.6; H.2; I.2 Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such as SQL. While this paradigm significantly improves usability and accessibility, it introduces new security risks, particularly the amplification of SQL injection vulnerabilities through the prompt-to-SQL translation process. Malicious users can exploit these mechanisms by crafting adversarial prompts that manipulate model behavior and generate unsafe queries. In this work, we propose a multi-layered security framework designed to detect and mitigate LLM-mediated SQL injection attacks. The framework integrates a front-end security shield for prompt sanitization, an advanced threat detection model for behavioral and semantic anomaly identification, and a signature-based control layer for known attack patterns. We evaluate the proposed framework under diverse and realistic attack scenarios, including prompt injection, obfuscated SQL payloads, and context-manipulation attacks. To ensure robustness, we generate and curate a comprehensive benchmark dataset of adversarial prompts and assess performance across a fine-tuned LLM configuration. Experimental results demonstrate that the proposed approach achieves high detection accuracy while maintaining low false-positive rates, significantly improving the secure deployment of LLM-powered database applications. |
| title | When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications |
| topic | Cryptography and Security Artificial Intelligence D.4.6; H.2; I.2 |
| url | https://arxiv.org/abs/2605.10176 |