An organisation that puts AI to work in cyber defence needs a mandate before it needs a model. Each use of AI, from an analyst's assistant to a red team's emulation agent, is either authorised, bounded and evidenced by policy, or it is improvisation that a supervisor, a works council or a court will later have to reconstruct. This chapter sets out that mandate, from policy and legal duties to rules of engagement as a signed and enforced artefact.
In CSF terms the chapter is responsible for GV.PO Policy in the Govern Function. Its Subcategories ask that policy is established from organisational context, strategy and priorities and is communicated and enforced (GV.PO-01), and that it is reviewed and updated as requirements, threats, technology and mission change (GV.PO-02) (19, NIST, 2024). With AI, "enforced" must cover an agent acting in milliseconds, and "changes in technology" a silently swapped vendor model. The chapter treats the Category through the three focus areas of the NIST Cyber AI Profile, currently a preliminary draft (20, NIST, 2025).
Covering AI requires no separate AI security policy, only that the existing policy says, for each way AI is used, who may use it, with which data, under which identity and with which evidence.
Primary topics explored
- Security policy that covers AI
- Duties that require testing and monitoring
- Threat-led testing: DORA TLPT and TIBER-EU
- The AI Act, data protection and labour law
- Acceptable use of offensive AI capabilities
- Rules of engagement as code
About AI Red Team
AI Red Team is Book 4 of The Transformed Architecture. It shows how large European enterprises and public authorities put artificial intelligence to work as an active part of cyber defence: AI-assisted red teaming and adversary emulation, red teaming of AI systems themselves, the AI-assisted security operations centre, detection engineering, threat intelligence, incident response and purple teaming, all under a lawful mandate and with evidence a supervisor can inspect.
It builds on the conclusions of Architecture as Code, AI Governance and AI Platform and Security.
CISOs, SOC leads, red and blue team practitioners, security architects, AI architects and technical decision-makers.
Gunnar Nordqvist
Conceived, directed and published the books of The Transformed Architecture.
Continue with the full chapter
Chapter 7: Policy, Mandate and Rules of Engagement in AI Red Team gives the detailed explanations, practical examples and implementation patterns behind this summary.
This whitepaper belongs to “Govern” and is one of 32 drawn from the manuscript.