Full course content for AI-201. 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-201: AI & Agentic Security II -- Course Outline →
Overview
Labs
- Lab 1: ATLAS Threat Mapping and Production Scope Declaration
- Lab 2: DVLA Baseline — Establishing an LLM Evaluation Regression Suite
- Lab 3: ML Supply Chain — Pickle Deserialization and Artifact Validation
- Lab 4: SSTI in LLM Pipelines (CVE-2025-9556 Family)
- Lab 4.5: GCG / AutoDAN / PAIR — Adversarial Suffix Lab
- Lab 5: Tool-Calling Exploit — Agency Confusion via Indirect Injection
- Lab 6: RAG Poisoning — Poisoned Vector Store and Exfiltration Chain
- Lab 7: SSRF via LLM-Generated URLs
- Lab 7.5: Visual Prompt Injection and Whisper Transcription-Chain Attack
- Lab 8: HarmBench Evaluation at Scale
- Lab 9: Memory-Persistence Injection
- Lab 10: Automated CVE Triage and ATLAS Enrichment Pipeline
- Lab 11: Multi-Model D8 Evaluation
- Lab 12: AI-201 Capstone
Other
- Module 1: From OWASP to ATLAS -- Production-Pentest Scoping
- Module 10: LLM-Powered Threat Intelligence Automation
- Module 11: The D8 Methodology in Depth — Full Comparative Evaluation
- Module 12: AI-201 Capstone — Coordinated Disclosure and Defensive Pipeline
- Module 2: The Virtus DVLA Testbed
- Module 3: Pickle / Cloudpickle / Dill Deserialization in Agentic Systems
- Module 4.5: The 2023-2026 Academic Jailbreak Corpus
- Module 4: Cross-Language SSTI -- The Bug-Class Generalisation
- Module 5: Tool-Calling Exploit Patterns
- Module 6: RAG-Poisoning and Indirect Prompt Injection at Scale
- Module 7.5: Multi-Modal Adversarial Attacks
- Module 7: Agentic Web-Scraping and SSRF in LLM-Rendered URLs
- Module 8: Adversarial Robustness Testing with HarmBench at Scale
- Module 9: Agentic Memory and Persistent Instruction Injection