🔒 Learning path

LLM Security & Guardrails

Learn to hack and defend Large Language Models.

0 of 7 complete

Explore common vulnerabilities like Prompt Injection, Jailbreaks, and Data Poisoning,
then learn how to defend your endpoints using specialized guardrail libraries.

What you'll learn

  1. 1. LLM Vulnerabilities & Red Teaming 🧪 Lab · 3 steps · 🔒 Subscriber ○
  2. 2. Implementing LLM Guardrails 🧪 Lab · 3 steps · 🔒 Subscriber ○
  3. 3. Vector Database RBAC 🧪 Lab · 2 steps · 🔒 Subscriber ○
  4. 4. PII Detection & Redaction in RAG Pipelines 🧪 Lab · 3 steps · 🔒 Subscriber ○
  5. 5. Federated Learning & Privacy-Preserving AI 🧪 Lab · 3 steps · 🔒 Subscriber ○
  6. 6. Audit & Provenance Logging for AI 🧪 Lab · 3 steps · 🔒 Subscriber ○
  7. 7. LLM Security - Knowledge Check ❓ Quiz · 🔒 Subscriber ○