Full course content for AI-301. The sidebar to the left lists every overview document, weekly module, and lab. Pick a starting point below or use the sidebar to jump anywhere.
Start here: AI-301: AI & Agentic Security III — Adversarial Capstone →
Overview
Labs
- Lab 2.1: Stack-Smash on Virtus OS v1
- Lab 3.1: L3-Regression Prompt Injection on DVLA
- Lab 4.5: SAE Feature Identification + Activation Steering on Llama-2-7B
- Lab 5.1: ROP Chain on Virtus OS + Paired Tool-Chain Hijack on DVLA
- Lab 6.1: Type Confusion on Virtus OS + Untyped-Output Exploitation on DVLA
- Lab 7.1: Cache-Timing Side Channel on Virtus OS + Latency Fingerprinting on DVLA
- Lab 7.5: Fine-Tuning Attack Reproduction + Booster Defense + Persistence Measurement
- Lab 8: Multi-Agent DVLA Topology
- Lab 9: OWASP LLM Audit
- Lab 10: RAG Poisoning on ChromaDB
Other
- Module 1: Re-Grounding -- Substrate vs Language Vulnerabilities
- Module 10: RAG Poisoning and Retrieval Attacks
- Module 11: Defenses -- Belt-5 Deployment Posture
- Module 12: Capstone Preparation and Course Synthesis
- Module 2: Stack-Smash on Virtus OS v1 -- Substrate Primer
- Module 3: Prompt Injection on DVLA -- Language Primer
- Module 4.5: Mechanistic Interpretability -- The Analogy Literalized
- Module 4: The Metaphor Named Precisely
- Module 5: ROP at the Substrate; Tool-Chain Hijack at the Language
- Module 6: Type Confusion at Substrate; Type Confusion at Language
- Module 7.5: Fine-Tuning Attacks as Supply-Chain Compromise
- Module 7: Side Channels -- Timing at Substrate; Latency at Language
- Module 8: Multi-Agent Attack Surfaces
- Module 9: OWASP LLM Top 10 Full Audit