Build LLM apps that are hard to abuse
AI Security and Privacy
The threat model for LLM applications, prompt injection, data leakage, tool abuse, privacy engineering and compliance basics, with a hands-on red-team lab.
2 tracks · 12 lessons · about 4 hours · 4 free lessons · 3 animated diagrams
What you will be able to do
- ✓Threat-model an LLM application end to end
- ✓Recognise and mitigate direct and indirect prompt injection
- ✓Apply least privilege to tools, agents and data access
- ✓Handle personal data and supply-chain risk responsibly
Who it is for
Developers shipping LLM features, plus security and privacy reviewers.
Prerequisites
Basic web-application knowledge. Building Applications track recommended.
Curriculum
Threats to LLM Apps
IntermediateThe LLM threat model, prompt injection, data leakage, insecure output handling and excessive agency.
- 1The LLM threat modelFree14 min
- 2Prompt injection: direct and indirect1 diagramFree15 min
- 3Data leakage and system prompt exposurePro14 min
- 4Insecure output handling and excessive agencyPro14 min
- 5Agent and MCP security: confused deputies, tool poisoning and least privilegePro17 min
- 6Model extraction, abuse and denial of walletPro14 min
Defense & Privacy
AdvancedLayered defenses, PII handling, supply-chain safety, compliance basics and a red-team lab.
- 1Defense in depth for LLM apps1 diagramFree14 min
- 2PII handling and local-first privacy1 diagramFree14 min
- 3Supply chain and stack securityPro14 min
- 4Compliance basics: GDPR, HIPAA and the EU AI ActPro14 min
- 5Lab: red-team your own LLM appLabPro60 min
- 6Red-team methodology, AI incident response and governancePro17 min