AI Red Teaming & Assurance is an advanced, six-week professional programme for practitioners who must probe AI systems for weakness before someone hostile does. It teaches authorised, structured adversarial testing of AI — threat modelling, prompt-injection and jailbreak testing, robustness and safety evaluation, governance assurance, and the running of an enterprise red-team programme — grounded in the realities of deploying AI in Nigerian organisations under the Nigeria Data Protection Act 2023 and a watching NDPC.
This is dual-use security education for defenders. Everything here is framed for authorised assurance work: testing systems you are permitted to test, under written scope, to make them safer. By the end you will be able to plan and run a responsible AI red-team engagement, evidence the findings, and feed them into a governance system that an auditor and a regulator will accept.
For: Security engineers, AI assurance and risk leads, internal auditors, ML engineers moving into safety, and governance professionals responsible for high-impact AI in banking, health, telecoms and the public sector.