Integrity-First AI Trust & Cybersecurity

Artificial intelligence systems increasingly make decisions in cybersecurity, finance, hiring, and healthcare but most are deployed without adequate governance, auditability, or accountability.

This 2-hour hands-on bootcamp introduces students to Integrity-First AI, a practical approach to securing and building trusted AI systems using cybersecurity principles.

Students will learn how AI systems fail in real-world scenarios (bias, prompt injection, hallucinations, data leakage), and how to apply governance controls aligned with modern frameworks such as the NIST AI Risk Management Framework and emerging regulations like the EU AI Act.

By the end of the session, students will have:

Broken a real AI system using attack techniques
Identified governance and compliance gaps
Implemented basic integrity controls (logging, filtering, traceability)
Understood how AI systems can be made auditable and trustworthy
This bootcamp introduces the future certification pathway in AI governance and integrity engineering.
Why will this be interesting?

70% hands-on (not lecture-heavy)
Cybersecurity framing (familiar to students)
Immediate “break and fix” learning loop
Aligns with real regulatory direction (EU AI Act / NIST AI RMF)
Learning Outcome

Students understand how to attack and secure AI systems using governance, compliance, and cybersecurity principles.