AI Red Teaming and Assurance Course (Self-Paced)
IDCYSE9008SP

The capstone of the applied AI security path, and the course that closes the loop between testing an AI system and being able to defend the decision to run it. It separates two things agencies routinely conflate: red teaming is deliberately trying to break, mislead or misuse a system, while assurance is the documented evidence that the system is trustworthy enough for its intended purpose. From there it runs the engagement lifecycle — scoping testing to the system's risk classification, setting objectives, writing rules of engagement (the difference between a red-team exercise and an incident), and handling team composition and deconfliction — then technique, matching method to attack surface and weighing expert-driven manual testing against automated approaches, on the principle that automation gives breadth and consistency while human testers give depth and creativity.

Two things set it apart. The first is agentic AI, where the attack surface expands from what a system says to what a system does — the most current idea in the course and the one buyers deploying AI agents are actually worried about. The second is the assurance half: most AI security training stops at finding problems, while this course covers building the assurance case as claim, argument and evidence, in the form an oversight body can actually audit, alongside Test, Evaluation, Verification and Validation records, model and system cards, and how documentation feeds a risk-acceptance decision. It also teaches genuinely difficult judgment calls — telling a red-team finding apart from an ordinary software bug, prioritizing by impact rather than technical complexity, and recognizing when a finding stops being a finding and becomes an incident. There is no lab, and that is deliberate: the SME replaced hands-on labs with scenario-based practice, including a prompt-assessment exercise where learners judge real example prompts from an engagement, so there is no environment to provision and the acquisition and oversight staff in the audience can take it alongside the testers. It sits at the top of a four-course ladder that runs from AI Security Fundamentals for the Cyber Workforce Course (Self-Paced) and AI Security & Governance for Government Course (Self-Paced) through Securing AI/ML Systems Course (Self-Paced) and AI Security Monitoring and Incident Response Course (Self-Paced).