Thursday, June 20, 2024

Hackers Use Text-to-SQL Attacks to Break into Your Databases

Recently, a group of researchers successfully demonstrated a new type of attack that utilizes Text-to-SQL models in order to generate malicious code.

The most astonishing thing about this malicious code is, it’s enough potential to obtain sensitive information and launch DDoS attacks on its targets.

An increasing number of database applications use artificial intelligence techniques to better communicate with users by translating human questions into SQL queries in order to provide a better experience.

Breaking Databases via Text-to-SQL Attacks

In order to produce malicious code, crackers can manipulate Text-to-SQL models by asking some specially designed questions. It is highly likely that the consequences will be serious since such code is executed automatically on the database.

It appears that it’s the first comprehensive empirical example of the use of NLP models as a vector for attack, and it was validated against two commercial solutions during the course of the study:-

  • AI2sql

An analogy to black-box attacks is the transfer of malicious payloads into the constructed SQL query, ushering to unexpected results when the malicious payload is embedded in the input question.

The malicious SQL queries that could be injected by specially crafted payloads could be weaponized. In order to modify the backend database, an attacker could run these queries on the server, as well as carry out a DoS attack on it.

As a further threat, a second category of attacks examined the possibility of compromising several PLMs so that malicious commands could be created when certain spurs were triggered.

A PLM-based system can be infiltrated by poisoning the training samples in many different ways, and these can be planted as backdoors.

There were four different open-source models that were attacked by the backdoors and here below we have mentioned below:-

  • T5-BASE
  • T5-3B

There was a 100% success rate with the use of a corpus poisoned with malicious samples, but there was no noticeable impact on performance when the corpus was used. Consequently, it is very difficult for these issues to be detected in a real-life situation.

Researchers stated that “Moreover, experiments involving four open-source frameworks verified that simple backdoor attacks can achieve a 100% success rate on Text-toSQL systems with almost no prediction performance impact”.


It was suggested by the researchers that the following mitigations could be taken:-

  • Integrate classifiers into the inputs of the program in order to detect suspicious strings
  • In order to prevent threats to the supply chain, off-the-shelf models must be assessed
  • The adoption of effective software engineering practices is essential
  • It is important to develop and use automation tools for the automation process
  • Acting immediately is the best course of action.

Secure Web Gateway – Web Filter Rules, Activity Tracking & Malware Protection – Download Free E-Book


Latest articles

1inch partners with Blockaid to enhance Web3 security through the 1inch Shield

1inch, a leading DeFi aggregator that provides advanced security solutions to users across the...

Hackers Exploit Progressive Web Apps to Steal Passwords

In a concerning development for cybersecurity, hackers are increasingly leveraging Progressive Web Apps (PWAs)...

INE Security: Optimizing Teams for AI and Cybersecurity

2024 is rapidly shaping up to be a defining year in generative AI. While...

Threat Actor Claims Breach of Jollibee Fast-Food Gaint

A threat actor has claimed responsibility for breaching the systems of Jollibee Foods Corporation,...

Threat Actors Claiming Breach of Accenture Employee Data

Threat actors have claimed responsibility for a significant data breach involving Accenture, one of...

Diamorphine Rootkit Exploiting Linux Systems In The Wild

Threat actors exploit Linux systems because they are prevalent in organizations that host servers,...

Amtrak Data Breach: Hackers Accessed User’s Email Address

Amtrak notified its customers regarding a significant security breach involving its Amtrak Guest Rewards...
Guru baran
Guru baran
Gurubaran is a co-founder of Cyber Security News and GBHackers On Security. He has 10+ years of experience as a Security Consultant, Editor, and Analyst in cybersecurity, technology, and communications.

Free Webinar

API Vulnerability Scanning

71% of the internet traffic comes from APIs so APIs have become soft targets for hackers.Securing APIs is a simple workflow provided you find API specific vulnerabilities and protect them.In the upcoming webinar, join Vivek Gopalan, VP of Products at Indusface as he takes you through the fundamentals of API vulnerability scanning..
Key takeaways include:

  • Scan API endpoints for OWASP API Top 10 vulnerabilities
  • Perform API penetration testing for business logic vulnerabilities
  • Prioritize the most critical vulnerabilities with AcuRisQ
  • Workflow automation for this entire process

Related Articles