Challenge: Existing studies on text-to-SQL systems have not investigated its security aspects . however, how to implement such attacks remains an open question.
Approach: They propose a backdoor-based SQL injection framework for text-to-SQL systems that uses boolean-based injection and union-based injecting techniques to exploit SQL injection vulnerabilities.
Outcome: The proposed framework can produce harmful SQL statements invalidating user queries or compromise sensitive information about the database.

Similar Papers

SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to Databases (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on the vulnerability of large language models to SQL injection have been limited.
Approach: They propose to evaluate the potential of language models to leak sensitive data when generating SQL queries.
Outcome: The proposed model with the best performance has an accuracy of 61.7%, compared to humans who achieve 94% accuracy.
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for textual backdoor attacks insert additional contents into normal samples as triggers, causing detection and blocking of backdoors.
Approach: They propose to use syntactic structure as trigger in textual backdoor attacks . they propose to achieve similar attack performance but have higher invisibility .
Outcome: The proposed method achieves almost 100% success rate but has higher invisibility and stronger resistance to defenses than the insertion-based methods.
BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents (2024.acl-long)

Copied to clipboard

Challenge: Xi et al., 2023) show that LLM-based intelligent agents are vulnerable to backdoor attacks.
Approach: They propose to build LLM-based intelligent agents using trained LLMs and fine-tune them on data for the agent task.
Outcome: The proposed methods are robust even after fine-tuning on trusted data.
Rethinking Stealthiness of Backdoor Attack against NLP Models (2021.acl-long)

Copied to clipboard

Challenge: Existing backdoor attacks are not stealthy to system deployers or users.
Approach: They propose a novel backdoor attack method based on negative data augmentation and modifying word embeddings that is much stealthier while maintaining pretty good attacking performance.
Outcome: The proposed method is much stealthier while maintaining pretty good attacking performance.
SQL Injection Jailbreak: A Structural Disaster of Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to jailbreak Large Language Models (LLMs) exploited internal properties or capabilities of the model, such as optimization-based jailbreak methods and methods that leveraged the model’s context-learning abilities.
Approach: They propose a new method which injects jailbreak information into user prompts and induces the model to generate harmful content.
Outcome: The proposed method achieves near 100% success rates on open-source models while incurring lower time costs compared to previous methods.
Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect (2022.coling-1)

Copied to clipboard

Challenge: text-to-SQL is a language processing and database-based language processing (NLP) task is to convert natural utterances into SQL queries and its practical application is to build natural language interfaces to database systems.
Approach: They propose to conduct a systematic survey of text-to-SQL to examine the challenges and potential future directions.
Outcome: The proposed system converts natural utterances into SQL queries and is a representative task in semantic parsing.
Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Recent models such as OpenAI o1 and DeepSeek-R1 produce explicit reasoning traces, often via Chain-of-Thought prompting.
Approach: They propose a taxonomy that offers a unified perspective for summarizing existing approaches and categorizing reasoning-based backdoor attacks into associative, passive, and active.
Outcome: The proposed taxonomy categorizes reasoning-based backdoor attacks into associative, passive, and active.
TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning (2025.findings-acl)

Copied to clipboard

Challenge: Despite the increasing support for multilingual capabilities, the impact of backdoor attacks on LLMs remains under-explored.
Approach: They propose to use poisoned instructiontuning data to attack multilingual LLMs . their results show that more powerful models show increased susceptibility to transferable cross-lingual backdoor attacks .
Outcome: The proposed attack is effective in models like BLOOM and GPT-4o with high success rates in more than 7 out of 12 languages.
Exploring Backdoor Vulnerabilities of Chat Models (2025.coling-main)

Copied to clipboard

Challenge: Recent studies show that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack.
Approach: They propose a backdoor attack method that distributes trigger scenarios across user inputs in different rounds and makes the backdoor be triggered only when all trigger scenarios have appeared in the historical conversations.
Outcome: The proposed method achieves high attack success rates on chat models while maintaining normal capabilities on providing helpful responses to benign user requests.
Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution (2021.acl-long)

Copied to clipboard

Challenge: Recent studies show that neural natural language processing models are vulnerable to backdoor attacks.
Approach: They propose to inject neural models with backdoors activated by word substitution . their results raise a serious alarm to the security of NLP models, they argue .
Outcome: The proposed backdoors are activated by a learnable combination of word substitution and exhibit higher invisibility than previous methods.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations