Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2308.01990 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909467421966336 |
|---|---|
| author | Pedro, Rodrigo Castro, Daniel Carreira, Paulo Santos, Nuno |
| author_facet | Pedro, Rodrigo Castro, Daniel Carreira, Paulo Santos, Nuno |
| contents | Large Language Models (LLMs) have found widespread applications in various domains, including web applications, where they facilitate human interaction via chatbots with natural language interfaces. Internally, aided by an LLM-integration middleware such as Langchain, user prompts are translated into SQL queries used by the LLM to provide meaningful responses to users. However, unsanitized user prompts can lead to SQL injection attacks, potentially compromising the security of the database. Despite the growing interest in prompt injection vulnerabilities targeting LLMs, the specific risks of generating SQL injection attacks through prompt injections have not been extensively studied. In this paper, we present a comprehensive examination of prompt-to-SQL (P$_2$SQL) injections targeting web applications based on the Langchain framework. Using Langchain as our case study, we characterize P$_2$SQL injections, exploring their variants and impact on application security through multiple concrete examples. Furthermore, we evaluate 7 state-of-the-art LLMs, demonstrating the pervasiveness of P$_2$SQL attacks across language models. Our findings indicate that LLM-integrated applications based on Langchain are highly susceptible to P$_2$SQL injection attacks, warranting the adoption of robust defenses. To counter these attacks, we propose four effective defense techniques that can be integrated as extensions to the Langchain framework. We validate the defenses through an experimental evaluation with a real-world use case application. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_01990 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application? Pedro, Rodrigo Castro, Daniel Carreira, Paulo Santos, Nuno Cryptography and Security Large Language Models (LLMs) have found widespread applications in various domains, including web applications, where they facilitate human interaction via chatbots with natural language interfaces. Internally, aided by an LLM-integration middleware such as Langchain, user prompts are translated into SQL queries used by the LLM to provide meaningful responses to users. However, unsanitized user prompts can lead to SQL injection attacks, potentially compromising the security of the database. Despite the growing interest in prompt injection vulnerabilities targeting LLMs, the specific risks of generating SQL injection attacks through prompt injections have not been extensively studied. In this paper, we present a comprehensive examination of prompt-to-SQL (P$_2$SQL) injections targeting web applications based on the Langchain framework. Using Langchain as our case study, we characterize P$_2$SQL injections, exploring their variants and impact on application security through multiple concrete examples. Furthermore, we evaluate 7 state-of-the-art LLMs, demonstrating the pervasiveness of P$_2$SQL attacks across language models. Our findings indicate that LLM-integrated applications based on Langchain are highly susceptible to P$_2$SQL injection attacks, warranting the adoption of robust defenses. To counter these attacks, we propose four effective defense techniques that can be integrated as extensions to the Langchain framework. We validate the defenses through an experimental evaluation with a real-world use case application. |
| title | From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application? |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2308.01990 |