topics

AI Security & Red Teaming

Prompt injection defense, jailbreak prevention, sandboxing, supply-chain AI package audits

4 lessons•~95 min•+120 XP
Module Progress
0%(0/4 completed)
Remaining to learn: 4

Lessons in Module (4)

lessons in order

Back to Track Overview
01
Prompt Injection Defense and Dual-LLM Architecture
#prompt-injection#dual-llm#llama-guard#nemo-guardrails#security#ai-engineering
25 min+30 XP
Read
02
Supply Chain Security: Defending Against Hallucinated Packages (Slopsquatting)
#slopsquatting#supply-chain#npm#packagist#security#ai-engineering
20 min+30 XP
Read
03
Sandboxing and Tool Isolation: Docker, gVisor and WASM for MCP
#mcp#sandboxing#docker#gvisor#wasm#security#ai-engineering
25 min+30 XP
Read
04
Automated Red Teaming and Jailbreak Testing for LLM Systems
#red-teaming#jailbreak#pyrit#giskard#evals#security#ai-engineering
25 min+30 XP
Read
Previous TopicAgentic Web, GEO & Multimodal
Back to Track Overview
Next TopicProduction RAG & GraphRAG