NIST SP 800-218A RV.1.2: Frequent, largely automated scanning and testing of models, with periodic audits (Medium)

What does RV.1.2 require?

To find vulnerabilities not yet detected, AI models are scanned and tested frequently, relying mainly on automation with a human in the loop as needed, and are audited periodically.

Maintained by Gerard Blokdyk

Other controls in Respond to Vulnerabilities (RV) – NIST SP 800-218A

RV.1.1 Gather vulnerability information, including from model input and output monitoring and AI vulnerability databases (High)
RV.1.3 Vulnerability disclosure and remediation policy covers AI models and informs users of limitations (Medium)
RV.2.1 Analyse each vulnerability, including deep analysis of model input and output deviations (Medium)
RV.2.2 Risk responses that allow for rebuild cost and for stopping or rolling back a model (High)
RV.3.1 Root cause analysis supported by after-the-fact review of training and alignment data (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