AI Red Teaming & Adversarial Testing
Not Started0 / 10 complete
Open a video or resource link, watch it, then check its box to track your progress and unlock what comes next.
10 lessons3 levels1 capstone project
Systematically attack and harden generative-AI and agentic systems using threat models, prompt-injection and jailbreak tests, adversarial test cases, automated red-team harnesses, abuse evaluation, mitigations and evidence-driven remediation.
BASIC
- AI Red Teaming 101: Full Course — Microsoft Developer (75 min)
Best end-to-end introduction to GenAI red teaming, prompt injection, jailbreaks, mitigations and PyRIT automation. - What Is a Prompt Injection Attack? — IBM Technology (8 min)
Build the core mental model for direct and indirect prompt injection and hostile context. - Prompt Injection Explained — JetBrains / PyCharm (12 min)
Connect model manipulation to tools, data access and unsafe agent actions.
INTERMEDIATE
- The Art of SLOs — Google
Apply AI Red Teaming & Adversarial Testing through the adjacent capability: Production Backend & Agentic Systems Engineering. - Raft — Martin Kleppmann
Apply AI Red Teaming & Adversarial Testing through the adjacent capability: Production Backend & Agentic Systems Engineering. - LLM Inference Optimization Explained
Apply AI Red Teaming & Adversarial Testing through the adjacent capability: AI Compute, Inference & Performance Engineering.
ADVANCED
- Let's Build GPT From Scratch — Andrej Karpathy
Extend AI Red Teaming & Adversarial Testing into senior/production practice through ML Foundations & GenAI. - AI Infrastructure on Kubernetes: Run:ai & KAITO — Microsoft / NVIDIA
Extend AI Red Teaming & Adversarial Testing into senior/production practice through AI Factory. - Securing AI agents on Azure — Microsoft Reactor
Extend AI Red Teaming & Adversarial Testing into senior/production practice through Agentic Security.