Udemy – AI Security Testing: Finding Sensitive Data Leaks

This course focuses on OWASP LLM-02: Sensitive Information Disclosure, one of the most important risks in the OWASP Top 10 for Large Language Model Applications. The problem is simple to describe and difficult to test correctly: can an LLM-based system reveal data the user should not be allowed to see? This course is designed for QA engineers, SDETs, automation engineers, and technical testers who want practical testing methods instead of theory alone.

You will learn how sensitive data leaks happen through:

• Runtime context and live session data
• Retrieval and authorization failures
• Aggregate inference and minimum-group threshold failures
• Training-data memorization behavior