United States

NIST SP 800-218A

42 controls. 0 other frameworks in our corpus share controls with it. Here is all of it, and how much of it you are already doing.

Page built . This page is derived from the framework corpus, which changes when the corpus is extended rather than daily.

42 controls 0 frameworks share controls with it United States verified against its source document

Every control below is one this framework asks for. The right hand column counts how many other frameworks in our corpus carry the same control, which is the difference between doing this work once and doing it again for the next standard.

There is no implementation kit for this framework yet. The control list and the overlap above are free and complete.

What you already have

Frameworks whose controls overlap this one, most first. If you run any of them, the count is roughly what you have already evidenced.

No measured overlap with another framework in the corpus.

Every control

CodeControlAlso in
1Purpose and audience of the Profile0
2Using the Profile: risk-based adoption, shared responsibility and model lineage limits0
PO.1.1Security requirements for development infrastructure and processes include AI model development (High)0
PO.1.2Policies carry the AI-specific security requirements for the software the organisation builds (High)0
PO.1.3Communicate AI model development security requirements to third-party component providers (Medium)0
PO.2.1Roles and responsibilities across the SDLC cover AI model development security (High)0
PO.2.2Role-based training covers AI model threats, vulnerabilities and mitigations (High)0
PO.2.3Leadership commitment to secure development involving AI models (Medium)0
PO.3.1Plan automated toolchains that secure AI model development (High)0
PO.3.2Deploy, operate and verify the AI security toolchains (High)0
PO.3.3Tools generate artefacts evidencing secure AI development, including dataset attestations (Medium)0
PO.4-5-unchangedPO tasks applied unchanged from SSDF 1.1: PO.4.2 (Low) and PO.5.2 (Medium)0
PO.4.1Security check criteria include guardrails across the AI development life cycle (Medium)0
PO.5.1Separate and protect each development environment, including training pipelines and model registries (High)0
PO.5.3Continuous monitoring of execution behaviour in development environments hosting AI models (High, new task)0
PS.1.1Store all code and model elements on least-privilege terms, with reward models and weights kept apart (High)0
PS.1.2Protect training, test, fine-tuning and alignment data from unauthorised access and change (High, new task)0
PS.1.3Protect model weights and configuration parameters (High, new task)0
PS.2.1Provide hashes or signatures for models, components and changes (Medium)0
PS.3.1Archive release files with versioned infrastructure tools, model selection rationale and training process records (Low)0
PS.3.2Provenance data for models, components, derivatives and the data behind them (Medium, modified task)0
PW.1-2-unchangedPW tasks applied unchanged from SSDF 1.1: PW.1.2, PW.1.3, PW.2.1, PW.4.2 and PW.9.10
PW.1.1Risk modelling that covers AI-specific threats (High)0
PW.3.1Analyse data for poisoning, bias, homogeneity and tampering before use (High, new task)0
PW.3.2Track data provenance where known and record where it is unknown (Medium, new task)0
PW.3.3Include adversarial samples in training and testing data under controlled use (Medium, new task)0
PW.4.1Acquire well-secured components, considering reuse of an existing model (High)0
PW.4.4Verify integrity, provenance and security of acquired models and components before use (High)0
PW.5.1Secure coding practice extended to AI, with careful handling of inputs and outputs (High)0
PW.6Build tool security features, with tool versions captured in provenance (PW.6.1 Low, PW.6.2 Medium)0
PW.7.1Code review and analysis policies cover AI model code (PW.7.1 Low)0
PW.7.2Scan all AI models for malware, vulnerabilities and backdoors (High)0
PW.8.1Code testing policies include AI models and the forms of testing to use (High)0
PW.8.2Test all AI models for vulnerabilities and retest after retraining or new data (High)0
PW.9.2Implement and document secure default settings for model administrators (Medium)0
RV.1.1Gather vulnerability information, including from model input and output monitoring and AI vulnerability databases (High)0
RV.1.2Frequent, largely automated scanning and testing of models, with periodic audits (Medium)0
RV.1.3Vulnerability disclosure and remediation policy covers AI models and informs users of limitations (Medium)0
RV.2.1Analyse each vulnerability, including deep analysis of model input and output deviations (Medium)0
RV.2.2Risk responses that allow for rebuild cost and for stopping or rolling back a model (High)0
RV.3-unchangedRV tasks applied unchanged from SSDF 1.1: RV.3.2, RV.3.3 and RV.3.4 (Medium)0
RV.3.1Root cause analysis supported by after-the-fact review of training and alignment data (Medium)0

Tell me when NIST SP 800-218A files something new

One email when a public company newly discloses something this framework governs, naming the company and what our corpus says it puts in scope. Nothing else, and one click to stop.

What this page is

A control-level reference for NIST SP 800-218A, drawn from our framework corpus. Control codes and titles are references to the standard, not reproductions of it. The overlap counts and the auditor artefacts are our own work and are the part you will not find elsewhere.

Measure this against what you already run · All frameworks · Today's edition