🛡️ Course · 10 lessons · about 6.4 hours

AI Security & LLM Security

Secure AI systems end to end: threat-model LLM apps, defend against prompt injection and data leakage, secure RAG, tools and agents, protect the model supply chain, red-team, monitor and govern.

Start lesson 1 →Roles: AI Security Engineer · Application Security Engineer · AI Engineer

Before you start

Generative AI & LLM EngineeringCybersecurity foundations

Part of these career paths

Agentic AI EngineerAI Security EngineerGenerative AI Developer

Module 1 · Threats to AI Systems

What attackers target in AI applications and how to model it.

  1. Lesson 0135 minThe AI Security Landscape — OWASP Top 10 for LLM ApplicationsWhy AI systems create new attack surfaces, the OWASP Top 10 for LLM applications, and MITRE ATLAS as a map of real attacks.
  2. Lesson 0240 minThreat Modelling AI SystemsMap data flows, trust boundaries and assets in an LLM app, then apply STRIDE-style analysis to prompts, retrieval, tools and outputs.
  3. Lesson 0340 minPrompt Injection and Jailbreaks — Direct and IndirectHow direct and indirect prompt injection and jailbreaks work, why there is no complete fix, and layered defences that reduce impact.

Module 2 · Securing AI Applications

Controls for data, retrieval, tools and models.

  1. Lesson 0440 minSecuring RAG — Document Permissions and Data LeakageEnforce per-user document permissions in retrieval, prevent cross-tenant leakage, and handle poisoned or untrusted documents.
  2. Lesson 0540 minSecuring Tools and Agents — Excessive Agency and SandboxingLeast-privilege tool design, confirmation for risky actions, sandboxed execution, and limiting what a compromised agent can do.
  3. Lesson 0635 minSensitive Data, Privacy and Output HandlingKeep PII and secrets out of prompts, logs and training data, treat model output as untrusted input, and meet privacy obligations such as the DPDP Act.
  4. Lesson 0735 minModel Supply Chain and Data PoisoningRisks in third-party models, datasets and packages, data and model poisoning, safe model formats, and verifying what you deploy.

Module 3 · Testing, Monitoring & Governance

Prove defences work and keep them working.

  1. Lesson 0840 minAI Red Teaming and Security TestingPlan an AI red-team exercise, build attack test suites, use automated scanners, and turn findings into regression tests.
  2. Lesson 0940 minMonitoring, Incident Response and AI GovernanceDetect abuse in production, respond to AI incidents, and apply governance frameworks such as the NIST AI RMF and the EU AI Act.
  3. Lesson 1040 minAI Security Interview PrepPrompt injection, RAG security, agent security and governance questions from AI security interviews, with model answers.