NIST SP 800-218A PO.2.2: Role-based training covers AI model threats, vulnerabilities and mitigations (High)

What does PO.2.2 require?

Role-based training for everyone whose work contributes to secure development includes an understanding of the cyber security vulnerabilities and threats that affect AI models and the ways they can be mitigated.

Maintained by Gerard Blokdyk

Other controls in Prepare the Organization (PO) – NIST SP 800-218A

PO.1.1 Security requirements for development infrastructure and processes include AI model development (High)
PO.1.2 Policies carry the AI-specific security requirements for the software the organisation builds (High)
PO.1.3 Communicate AI model development security requirements to third-party component providers (Medium)
PO.2.1 Roles and responsibilities across the SDLC cover AI model development security (High)
PO.2.3 Leadership commitment to secure development involving AI models (Medium)
PO.3.1 Plan automated toolchains that secure AI model development (High)
PO.3.2 Deploy, operate and verify the AI security toolchains (High)
PO.3.3 Tools generate artefacts evidencing secure AI development, including dataset attestations (Medium)

Query this from an agent

The graph holds this control, the 0 it maps to, and the evidence behind each claim, over MCP and REST.

MCP endpoint All NIST SP 800-218A controls