jnaapti

AI curriculum

Course outline for AI Security Foundations

AI features introduce new paths for untrusted input and tool misuse. Threat-model a small application and design layered controls for data and execution boundaries.

Technology
AI Security, Governance and Trust
Duration
4 hours
Modules
2 · 2 hours each
Level
Prerequisites listed

About AI Security Foundations

AI features introduce new paths for untrusted input and tool misuse. Threat-model a small application and design layered controls for data and execution boundaries.

AI Security Foundations Course Objectives

  • Identify AI-specific threats and trust boundaries.
  • Analyze controlled prompt injection examples.
  • Propose layered controls and verification checks.

Pre-requisites

  • Familiarity with AI application behavior.
  • Basic application security and data access concepts.

Lab Setup

  • Computer with a browser and a local mock application.
  • Use synthetic data and harmless security fixtures only in an authorized disposable environment.

Detailed Course Outline

Proposed modules

Module 1: Input and data threats

  • AI threat models
  • Prompt injection
  • Jailbreaking
  • Data leakage

Practical outcome: Map untrusted inputs and potential data exposure paths.

Module 2: Execution and dependency risks

  • Tool abuse
  • Model abuse
  • Supply-chain risk
  • OWASP guidance

Practical outcome: Select controls for tools and dependencies using a threat model.

Practical exercise

  • Review a mock AI application and test a defensive control using harmless attack fixtures.

How we train

Contact us for full course details, including duration, delivery options and lab requirements.

Ask about exercises, instructor feedback and the prior knowledge you need. Tool-specific courses marked provisional may become modules in a broader course.

Discuss your learning goals