STALE MEASUREMENTPast this project's own 2-release window: the published result was measured with v0.32.0, 9 releases ago. Why, and what unblocks it

ProvaelStar on GitHubQuickstart
ProductEvidenceTop 10LeaderboardCompliancePricingDocsStar on GitHub Quickstart
NIST AI 100-1 · Generative AI Profile (NIST AI 600-1)

NIST AI RMF

The NIST AI Risk Management Framework is a voluntary, widely-adopted structure for identifying and managing AI risk across four functions: Govern, Map, Measure, Manage. Provael produces evidence for the Measure and Manage functions.

Voluntary framework; widely referenced by auditors and procurement.Evidence, not certification.
What it is

The framework

  • NIST AI 100-1 defines the core AI RMF; the Generative AI Profile (NIST AI 600-1) extends it.
  • It is voluntary but frequently cited in US procurement and by third-party auditors as a maturity yardstick.
  • The Measure function is about analysing, assessing and tracking AI risks with repeatable metrics.
  • NIST AI 100-2e2025 provides the adversarial-ML taxonomy Provael names its attacks against (privacy attacks map to NISTAML.03).
The hook

Where a red-team result fits

Measure 2.7

The AI RMF subcategory “AI system security and resilience - as identified in the MAP function - are evaluated and documented” asks for exactly this evidence - Provael positions the measured ASR, its 95% CI and the benign-FPR control as the evaluation, and the SARIF + signed attestation bundle as the documentation.

Measure

Quantify AI risks and trustworthiness characteristics with repeatable, documented methods - an ASR with a CI and a benign control fits directly.

Manage

Prioritise and act on measured risks; a CI red-team gate operationalises the Manage function in the development loop.

What Provael maps to it

Evidence produced

  • Measure: an attack-success rate with a benign control and confidence interval, tracked over time.
  • Manage: a CI gate that acts on the measurement and blocks regressions.
  • Documentation and reproducible traces supporting the Govern function’s evidence trail.
Timing

Dates (verified 19 Aug 2026)

AI RMF 1.0 released
January 2023
Generative AI Profile
July 2024

Not legal advice; verify the live EUR-Lex/ISO text at launch before relying on these dates.

Sources

Primary references

How to read this mapping

What it is - and isn’t

  • adversarial-only - Provael measures adversarial robustness - susceptibility to manipulation - not general accuracy, reliability, or functional safety.
  • evidence-not-certification - The output is evidence you file, not a certificate. Provael is not a notified body, a lab, or a certification scheme.
  • behavioural-not-worst-case - The measured result uses templated, auditable attacks; the search-based families (optimized, universal_patch, gradient_patch) have only met the CPU fixture. Results are a floor on susceptibility - a behavioural lower bound, not a certified worst-case bound.
Evidence, not certification

Running Provael does not make a system compliant or certified - it generates measurements you can put into a conformity or assurance file.

Independent project. Not affiliated with or endorsed by ISO, the EU, NIST, IEC, OWASP, or MITRE. Not legal advice.

Clause references are indicative; a wrong clause citation is worse than a missing one.

Turn this into filed evidence.

Download the redacted sample pack, or book an assessment to get the crosswalk filled in for your policy.

Sample SARIF ↓Book an assessment