Learning Paths
5 curated sequences — structured curricula that guide you from foundations to advanced techniques in each area of AI security.
AI Security Foundations
A beginner-accessible sequence from threat taxonomy through to incident response — the essential first curriculum for anyone entering AI security.
For: Security practitioners new to AI, ML engineers learning threat modeling, or anyone who wants a structured overview before diving deeper.
Securing AI Agents
End-to-end security for autonomous LLM agents — from credential hygiene through multi-agent trust, runtime controls, and zero-trust architecture.
For: Engineers building or operating agentic AI systems, platform security teams, and architects designing multi-agent pipelines.
Privacy & Data Protection
From differential privacy mathematics through training data extraction, membership inference, and privacy-preserving inference — how AI systems leak information and how to stop them.
For: ML engineers, privacy engineers, and security researchers concerned with data leakage from trained models and inference pipelines.
Red Team / Offense Perspective
The attacker's view: jailbreaks, injection vectors, supply chain compromise, tool poisoning, and AI weaponised against traditional infrastructure.
For: Red teamers, offensive security researchers, and defenders who want to understand attacks at a technical depth that informs better mitigations.
Enterprise AI Governance
From shadow AI risk through regulatory compliance, production monitoring, guardrail design, vulnerability disclosure, and incident response — the practitioner's governance stack.
For: CISOs, security architects, compliance engineers, and anyone operationalising AI security at enterprise scale.