Source |
The Hacker News |
Identifiant |
8299223 |
Date de publication |
2023-01-09 19:07:00 (vue: 2023-01-09 14:05:55) |
Titre |
New Study Uncovers Text-to-SQL Model Vulnerabilities Allowing Data Theft and DoS Attacks |
Texte |
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 |
Envoyé |
Oui |
Condensat |
academics adversaries allowing applications attacks better can code could data database demonstrated denial dos employ enable glean group has human information interact leverage malicious model models namely text new novel peng produce queries questions range sensitive service sql stage study techniques text theft translate uncovers users vulnerabilities wide xutan |
Tags |
|
Stories |
|
Notes |
★★★
|
Move |
|