AI Security Engineer
Protect AI systems from attacks, data leaks and misuse.
Threat modeling, prompt injection, data leakage, agent and tool security, supply chain risk, red teaming, guardrails and monitoring, and incident response. Ends with interview practice.
10 lessons · about 3 hours
Certificate of completion
Earn your AI Security Engineer certificate
Verified edition
Mark every lesson in this course complete. You have finished 0 of 10. 10 to go.
See a sample certificate. Anyone can check a certificate with its code at /verify. It records course completion. It is not an exam or an accredited qualification.
What is new about AI security, what stays the same and what the role covers.
Draw the system, mark trust boundaries, ask the right questions and rank the threats.
Direct and indirect injection, common attack patterns and layered defenses.
Where data leaks, how to keep customers apart and which controls work.
Least privilege, tool-call checks, human approval, sandboxes and tool server risks.
Models, packages, data, tool servers and prompts as entry points, and how to reduce the risk.
Plan a safe exercise, try the main attacks, record findings and turn them into regression tests.
Input and output checks, plain-code limits, what to log and what to alert on.
A playbook from the first alert to the blame-free review, with points special to AI.
Common questions with strong answers, a design method and a portfolio that proves your skill.