Ai Security Testing: Finding Sensitive Data Leaks

Ai Security Testing: Finding Sensitive Data Leaks
Published 5/2026
Created by Jonathan Fisher
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz, 2 Ch
Level: All Levels | Genre: eLearning | Language: English | Duration: 45 Lectures ( 1h 24m ) | Size: 530 MB​

Test LLM apps for OWASP LLM-02 sensitive information disclosure with practical QA workflows
What you'll learn
Identify OWASP's LLM-02 Sensitive Information Disclosure risks in model outputs, retrieval results, runtime context, and training data
Design QA test cases that use clear personas, prompt strategies, fail signals, and synthetic data to detect disclosure failures
Validate suspected leaks by comparing model output against known test data and separating real disclosures from hallucinations
Report LLM-02 bugs with reproducible evidence, attack path, disclosure impact, failed layer, remediation, and closure criteria
Requirements
A fundamental understanding of Software Testing (QA)
A basic familiarity with LLMs and Prompting
Description
Large Language Models are changing how software is built. They are also creating new failure paths that traditional QA workflows were never designed to test.
This course focuses onOWASP LLM-02: Sensitive Information Disclosure, one of the most important risks in theOWASP 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 forQA 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
You will learn how to
Design structured LLM-02 test plans
Build hypothesis-driven test cases
Define clear fail signals
Separate real disclosures from hallucinations
Capture reproducible evidence
Write actionable bug reports
Verify fixes through repeatable testing and regression coverage
The course includes hands-on demonstrations using synthetic data and realistic scenarios. You will see practical QA workflows that can be applied directly to AI-enabled products.
By the end of the course, you will have a repeatable process for testing sensitive information disclosure risks and converting confirmed failures into long-term regression coverage.
This course builds on the same QA-first approach used throughout the OWASP LLM course series.
AI Usage Disclosure
AI tools were used during course development to support brainstorming, editing, structure review, and iterative content refinement. All technical content, demonstrations, workflows, and QA guidance were reviewed, validated, and adapted by the instructor for accuracy and practical use.
No course content was generated and published without instructor review and revision.
Who this course is for
QA Engineers and Software Testers
AI Product Owners and Developers

You do not have permission to view the full content of this post. Log in or register now.