Free account = 1 chapter of every course unlocked
No credit card · Google sign-in in 30 seconds · 17+ free chapters across 17 courses
Start free →
All Courses/AI Security, Guardrails, and Red Teaming
🛡️

AI Security, Guardrails, and Red Teaming

Threat modeling, prompt injection, agent risks, data security, red teaming, monitoring, and compliance for production AI.

12 chaptersFirst chapter free to preview

Full syllabus

1

Foundations and Threat Modeling

Free preview
Read free →
2

Prompt Injection and Instruction Attacks

3

Insecure Outputs and Downstream Risk

4

Tools, Agents, and Excessive Agency

5

Data Security, Privacy, and Secrets

6

Identity, Permissions, and Trust Boundaries

7

Guardrails, Validation, and Policy Enforcement

8

Red Teaming and Adversarial Testing

9

Monitoring, Incident Response, and Auditability

10

Secure Architecture Patterns for AI Systems

11

Compliance, Governance, and Enterprise Controls

12

Capstones, Case Studies, and Security Readiness

Unlock all 12 chapters

Plus 18 other courses — 344 more chapters included.

Compare all plans

Free Tools & Calculators