AI Security & Red Teaming
Master AI security: prompt injection, jailbreaks, data leakage, OWASP Top 10 for LLMs, red teaming methodology, and defense-in-depth. Pulls from the AI Security course, the Evaluation & Safety phase, and the Vibe Coding Security Review project.
The route
- Evaluation & Safety — security modules — ML & AI Engineering (phase 08). The red teaming & safety lessons within the Evaluation phase: prompt injection, jailbreaks, data leakage, OWASP Top 10 for LLMs, and safety guardrails.
- AI Security & Red Teaming (full course) — AI Security & Red Teaming. A complete career track on AI security: threat modeling, attack vectors, red team methodology, defense strategies, and building secure AI systems.
- Security Review for Vibe Coders — Security Review for Vibe Coders. A weekend project on security review for AI-generated code: finding vulnerabilities in vibe-coded apps, secrets management, and secure coding patterns.
What you build
A red team report with implemented defenses, a threat model document, and a secure AI system with input validation, output filtering, and PII masking.
Every learning path
Create a free account — the opening phases of 24 of 30 courses are free, no credit card. Or see Pro pricing.
All courses · Pricing · About · FAQ · Glossary