Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks

Summary: Study of backdoor vulnerabilities in LLM Text-to-SQL: ToxicSQL uses stealthy command-like and character-level triggers to hide backdoors while keeping benign accuracy. Demonstrates executable SQL-injection backdoors with 79.41% success using only 0.44% poisoned data and offers defenses. (summarized by gpt-5-mini on Feb 11 2026)

Paper ID: 7358
Venue: SIGMOD
Year: 2026
Pagerank: 4.1945683e-05
Overall Rank: 10,051 | 30.08%
DOI: 10.1145/3769762

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
369	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.0002547515
998	CodeS: Towards Building Open-source Language Models for Text-to-SQL	2024	SIGMOD	0.00014729379
1,732	CatSQL: Towards Real World Natural Language to SQL Applications	2023	VLDB	0.00010732004
2,433	ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems	2024	VLDB	8.8285962e-05
2,945	Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning	2023	SIGMOD	7.8377395e-05
3,662	The Dawn of Natural Language to SQL: Are We Fully Ready?	2024	VLDB	6.8672143e-05
3,859	OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment	2025	SIGMOD	6.6907933e-05
4,908	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB	5.8339245e-05
5,033	FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis	2024	SIGMOD	5.7486224e-05
7,354	Reliable Text-to-SQL with Adaptive Abstention	2025	SIGMOD	4.7529612e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
998	CodeS: Towards Building Open-source Language Models for Text-to-SQL	2024	SIGMOD	0.00014729379
11,058	LLM-PBE: Assessing Data Privacy in Large Language Models	2024	VLDB	4.1945683e-05
7,139	Automated Validating and Fixing of Text-to-SQL Translation with Execution Consistency	2025	SIGMOD	4.821174e-05
3,978	OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale	2025	VLDB	6.5725884e-05
4,908	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB	5.8339245e-05
10,451	RTS+: Reliable Text to SQL	2025	SIGMOD	4.1945683e-05
7,354	Reliable Text-to-SQL with Adaptive Abstention	2025	SIGMOD	4.7529612e-05
10,837	Natural Language to SQL: State of the Art and Open Problems	2025	VLDB	4.1945683e-05
10,268	OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision	2026	VLDB	4.1945683e-05
369	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.0002547515