Shared AI core
Model limits and evaluation in a security context.
Stage outcomeThe specialist understands AI-specific failure modes and can separate model behavior from security guarantees.
Interactive roadmap
Cybersecurity Specialist + AI
Threat modeling, red teaming, and AI system protection
A path for security specialists covering prompt injection, data leakage, agent permissions, model supply-chain security, sandboxing, AI red teaming, and incident response.
10–16 weeksSecurity engineersAppSecSOC analystsRed teamers
Open as course →Every node has an evidence route
3stages
11nodes
2projects and milestones
- 02
AI threat model
Attacks against prompts, data, tools, models, and the AI supply chain.
Stage outcomeThe system has an explicit threat model, mapped controls, and repeatable security tests.Materials readyAssessment availableMaterials readyMaterials readyAssessment availableMaterials readyAssessment availablePrerequisites: Prompt injection and data exfiltration, Agent permissions and tool abuse - 03
Red teaming and incident response
Adversarial evaluation, monitoring, containment, recovery, and lessons learned.
Stage outcomeAI security regressions are detected before release and contained quickly in production.Materials readyMaterials readyMaterials readyAssessment availableMaterials readyPrerequisites: AI red teaming, Security evaluations in CI, AI incident response