AI security
What does AI security cover in AI governance?
4 competencies are filed under it: Agentic AI controls and authorization boundaries, AI incident response and recovery, Privacy by design and privacy engineering, AI security fundamentals. Each has its own page saying what it means in practice.
The competencies filed under it
- Agentic AI controls and authorization boundaries
Governs AI agents that take actions: tool access, least privilege, interruptibility, cascading actions and accountability for what an agent did.
Governance and Oversight
- AI incident response and recovery
Classifies AI incidents by severity, runs containment, preserves evidence, manages notification, and closes the loop with lessons learned.
Risk and Assurance
- Privacy by design and privacy engineering
Builds minimization, purpose limitation, de-identification, consent and retention into an AI system before launch, with tests that prove it.
Data and Privacy
- AI security fundamentals
Understands prompt injection, data poisoning, model theft, insecure integrations and excessive agent privileges, and the controls that reduce each.
Security and Resilience
Roles that ask for it
- Agentic AI Engineer, orchestration edition3 of 4 competencies
- AI Security Architect3 of 4 competencies
- Chief Information Security Officer, AI security focus3 of 4 competencies
- Cybersecurity Risk Analyst2 of 4 competencies
- AI Evaluation Specialist2 of 4 competencies
- AI Governance Engineer2 of 4 competencies
- AI Privacy Engineer2 of 4 competencies
- AI Incident Response Lead2 of 4 competencies
- Chief Privacy Officer, AI privacy edition2 of 4 competencies
- Chief Technology Officer, AI engineering edition2 of 4 competencies
- Privacy Analyst1 of 4 competency
- Third-Party AI Risk Analyst1 of 4 competency
- AI Auditor1 of 4 competency
- AI Engineer, production systems edition1 of 4 competency
- AI Product Manager, responsible product edition1 of 4 competency
- AI Risk Manager1 of 4 competency
- AI Vendor Risk Manager1 of 4 competency
- Operations Manager, AI-ready1 of 4 competency
- Security Compliance Manager1 of 4 competency
- Third-Party Cyber Risk Manager1 of 4 competency
- AI Regulatory Counsel1 of 4 competency
- Physical AI Safety Engineer, autonomous systems edition1 of 4 competency
- Chief Information Officer, technology leadership edition1 of 4 competency
- Chief Risk Officer, AI risk edition1 of 4 competency
- VP of AI Governance and Ethics1 of 4 competency
Where it is taught and graded
73 graded topics, each passed by explaining it back. The first module of every program is free with a free account.
- Module 0: Taking the Controls (2)
- Module 1: The Agent, Deconstructed (1)
- Module 2: Capability and Autonomy (1)
- Module 3: Bounding by Design (1)
- Module 4: Meaningful Human Accountability (1)
- Module 5: Technical Controls and Threat Modeling (5)
- Module 6: Testing and Red-Teaming (2)
- Module 7: Rollout, Monitoring, and Incident Response (2)
- Module 1: Digital Foundations (1)
- Module 2: AI Fundamentals (1)
- Module 3: Ethical and Responsible AI and Operational Governance (1)
- Module 9: Agentic AI and Workforce Integration (2)
- Module 10: AI Security Fundamentals (6)
- Module 11: Bonus: AI Leadership Accelerator (1)
- Module 3: Shipping AI and Surviving the Incident (3)
- Module 7: Agents Under Command (4)
- Module 8: The Money: Budgets, ROI, and Risk (1)
- Module 10: Evidence Engineering (3)
- Module 4: Feeding the Machines (1)
- Module 5: Poison, Leaks, and the Adversary (3)
- Module 6: Access and the Keys (3)
- Module 11: Data Incidents (2)
- Module 10: Privacy and Data Governance (4)
- Module 17: AI Governance, AI Risk, AI Security, and AI Assurance (4)
- Module 18: Governance, Risk and Compliance Technology, Automation, and Evidence Engineering (1)
- Module 9: Risk, Resilience and Frontier AI (4)
- Module 15: Lab: Regulated Industries (1)
- Module 5: Data Security for AI (2)
- Module 6: Ethics Review (1)
- Module 8: Enforcement and Incident Response (2)
- EU AI Act Implementation Expert3 topics
- Module 3: High-Risk AI Requirements: The Technical File (1)
- Module 8: Post-Market Monitoring and Enforcement (2)
- Module 10: Responsible Physical AI in Practice (2)
- Module 11: Crisis Management and Controversy Navigation (1)
- Module 23: Technical Credibility Deep Dive (1)
Questions
- What does AI security cover in AI governance?
- 4 competencies are filed under it: Agentic AI controls and authorization boundaries, AI incident response and recovery, Privacy by design and privacy engineering, AI security fundamentals. Each has its own page saying what it means in practice.
- Which roles ask for AI security?
- 25 roles on the map name at least one of its competencies, from analyst seats to executive ones. Each role page lists the depth expected.
- Where is AI security taught and graded?
- 73 graded topics teach it across 10 programs. Each topic is graded by explaining it back against its own transcript, so a pass is evidence, not attendance. The first module of every program is free with a free account.