Course Tracks
AI Security
Threat modeling, prompt injection, model risk, and securing AI applications in production. Built by security engineers who operate AI systems under real threat conditions.
The AI Security Problem
AI Extends your Attack Service
Every LLM integration, every AI-assisted workflow, and every model deployment creates new risk surfaces that traditional security training doesn’t cover.
Prompt Injection & Jailbreaks
Direct and indirect prompt injection, jailbreak techniques, and the defenses that actually hold. Understand how attackers manipulate LLM behavior and build systems that resist it.
Model Supply Chain Risk
Risks introduced by third-party models, fine-tuning pipelines, and model registries. Data poisoning, model backdoors, and what due diligence looks like for ML supply chains.
Data Exfiltration via AI
How AI systems become exfiltration vectors. Prompt leakage, system prompt extraction, and building LLM applications that don't accidentally expose sensitive data.
AI Governance & Risk Frameworks
OWASP Top 10 for LLMs, NIST AI RMF, and EU AI Act compliance. How to build governance programs that work for teams actually deploying AI in production.
Courses in this track
Available Now
Prompt Injection & LLM Attack Surfaces
Understand how prompt injection, jailbreaks, and indirect injection attacks work—and how to build defenses that hold up in production AI systems.
Advanced
Self-Paced
AI Model Risk & Governance
Risk frameworks, model cards, and governance practices for teams deploying AI in regulated or high-stakes environments.
Intermediate
Self-Paced