New cohorts enrolling monthly — onsite, online & hybrid formats. Modern SQA Formula Bootcamp 2026 Registration ongoing Corporate teams: ask about custom bootcamp pricing.
AI security team testing prompts retrieval tools permissions and sensitive data boundaries
SQA, Test Automation & SDET · Course #061

AI Security & Data Privacy Testing

AI Security & Data Privacy Testing gives learners a structured route to test security and privacy controls across AI data, models, prompts, retrieval, tools and outputs. The learning begins with ai security architecture, assets and trust boundaries before connecting the subject to threat modelling prompts, retrieval, models, tools and data and direct and indirect prompt-injection testing. Participants build a threat-informed test plan covering prompt injection, data exposure, insecure tool use, model or supply-chain risks, privacy leakage and logging, with safe red-team boundaries and remediation verification. Activities emphasise evidence, traceability and sound judgement, so participants can explain why a technique is appropriate instead of following steps mechanically. They connect AI-specific attack paths to established access, data-protection and secure-testing principles.

Enroll Interest Back to Courses

Overview

AI Security & Data Privacy Testing gives learners a structured route to test security and privacy controls across AI data, models, prompts, retrieval, tools and outputs. The learning begins with ai security architecture, assets and trust boundaries before connecting the subject to threat modelling prompts, retrieval, models, tools and data and direct and indirect prompt-injection testing. Participants build a threat-informed test plan covering prompt injection, data exposure, insecure tool use, model or supply-chain risks, privacy leakage and logging, with safe red-team boundaries and remediation verification. Activities emphasise evidence, traceability and sound judgement, so participants can explain why a technique is appropriate instead of following steps mechanically. They connect AI-specific attack paths to established access, data-protection and secure-testing principles.

Course Highlights

AI threat modelling

Prompt injection and untrusted input

Sensitive-data and privacy leakage tests

Tool and permission boundaries

Model and component supply-chain risk

Safe red-team evidence

Modules & Curriculum

AI security architecture, assets and trust boundaries

Threat modelling prompts, retrieval, models, tools and data

Direct and indirect prompt-injection testing

Sensitive-information disclosure and privacy leakage

Authentication, authorisation and excessive agency

Retrieval poisoning, memory and context-isolation risks

Insecure output handling and downstream tool effects

Model, dependency and data supply-chain concerns

Logging, retention, incident evidence and privacy

Controlled red-team plan, report and remediation retest

Learning Outcomes

  • Map AI assets, trust boundaries and plausible threat actors.
  • Design controlled prompt-injection and data-exposure tests.
  • Verify identity, authorisation and least-privilege controls for tools.
  • Assess retrieval, memory, logs and outputs for privacy leakage.
  • Evaluate third-party model and component risks.
  • Report and retest findings with reproducible evidence and safe boundaries.

Ready to Build Your Future-Ready Skills?

Probe AI attack paths and privacy failures with controlled, evidence-led testing.

Enroll Interest

Related Courses

Beginner Junior QA learners mapping assurance activities across a software delivery lifecycle

Software Quality Assurance (SQA) Fundamentals

View Course
Beginner Software team tracing requirements through development testing release and maintenance stages

Software Development Life Cycle (SDLC)

View Course
Beginner QA trainees organising test planning execution defect tracking and closure artefacts

Software Testing Life Cycle (STLC)

View Course