New Study Uncovers Text-to-SQL Model Vulnerabilities Allowing Data Theft and DoS Attacks,
A group of academics has demonstrated novel attacks that leverage Text-to-SQL models to produce malicious code that could enable adversaries to glean sensitive information and stage denial-of-service (DoS) attacks.
“To better interact with users, a wide range of database applications employ AI techniques that can translate human questions into SQL queries (namely Text-to-SQL),” Xutan Peng, a
“To better interact with users, a wide range of database applications employ AI techniques that can translate human questions into SQL queries (namely Text-to-SQL),” Xutan Peng, a
,
A group of academics has demonstrated novel attacks that leverage Text-to-SQL models to produce malicious code that could enable adversaries to glean sensitive information and stage denial-of-service (DoS) attacks.
“To better interact with users, a wide range of database applications employ AI techniques that can translate human questions into SQL queries (namely Text-to-SQL),” Xutan Peng, a
“To better interact with users, a wide range of database applications employ AI techniques that can translate human questions into SQL queries (namely Text-to-SQL),” Xutan Peng, a
, ,
https://thehackernews.com/2023/01/new-study-uncovers-text-to-sql-model.html