Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910981134745600 |
|---|---|
| author | Klisura, Đorđe Rios, Anthony |
| author_facet | Klisura, Đorđe Rios, Anthony |
| contents | Text-to-SQL systems empower users to interact with databases using natural language, automatically translating queries into executable SQL code. However, their reliance on database schema information for SQL generation exposes them to significant security vulnerabilities, particularly schema inference attacks that can lead to unauthorized data access or manipulation. In this paper, we introduce a novel zero-knowledge framework for reconstructing the underlying database schema of text-to-SQL models without any prior knowledge of the database. Our approach systematically probes text-to-SQL models with specially crafted questions and leverages a surrogate GPT-4 model to interpret the outputs, effectively uncovering hidden schema elements -- including tables, columns, and data types. We demonstrate that our method achieves high accuracy in reconstructing table names, with F1 scores of up to .99 for generative models and .78 for fine-tuned models, underscoring the severity of schema leakage risks. We also show that our attack can steal prompt information in non-text-to-SQL models. Furthermore, we propose a simple protection mechanism for generative models and empirically show its limitations in mitigating these attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14545 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems Klisura, Đorđe Rios, Anthony Computation and Language Text-to-SQL systems empower users to interact with databases using natural language, automatically translating queries into executable SQL code. However, their reliance on database schema information for SQL generation exposes them to significant security vulnerabilities, particularly schema inference attacks that can lead to unauthorized data access or manipulation. In this paper, we introduce a novel zero-knowledge framework for reconstructing the underlying database schema of text-to-SQL models without any prior knowledge of the database. Our approach systematically probes text-to-SQL models with specially crafted questions and leverages a surrogate GPT-4 model to interpret the outputs, effectively uncovering hidden schema elements -- including tables, columns, and data types. We demonstrate that our method achieves high accuracy in reconstructing table names, with F1 scores of up to .99 for generative models and .78 for fine-tuned models, underscoring the severity of schema leakage risks. We also show that our attack can steal prompt information in non-text-to-SQL models. Furthermore, we propose a simple protection mechanism for generative models and empirically show its limitations in mitigating these attacks. |
| title | Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.14545 |