AI Security Testing
Enable practitioners to plan, run and report AI security testing as a disciplined, authorised and repeatable activity: scoping with rules of engagement, deriving tests from threat models, designing scenarios, testing adversarial inputs safely, measuring results credibly, handling live findings as incidents and writing reports that drive remediation.
Upcoming course. LMS delivery and enrolment are not open. Release dates will be confirmed.
Express interest →
Planned learning outcomes
- Scope an AI security test and agree rules of engagement with the system owner
- Derive prioritised test objectives from a threat model, using recognised AI threat frameworks
- Design test scenarios and cases with expected safe behaviour, pass criteria and coverage
- Plan adversarial prompt testing that is safe, authorised and does not create harmful artefacts
- Evaluate results with sound metrics, repeat runs and severity ratings
- Escalate live findings through incident response and track remediation to retest
- Write an AI security testing report that decision makers and engineers can act on