STALE: OUR MEASUREMENT

Our published benchmark result was measured with v0.41.2, 5 releases ago, past this project's own 2-release window, and the newest real-model measurement, dated 2026-09-18, is past this project's own 7-day window. That is our own number, not your assessment, which runs against your policy on the current release. Why, and what unblocks it

STALE: REGULATORY CLOCK

The regulatory entries on this page were last checked against their primary sources on — 34 days before this build’s anchor of , past this project’s own 30-day window. Every date here was true when it was read and has not been re-read since. Verify against the primary source before relying on it. The clock, with every source

ProvaelGitHub, star the repositoryQuickstart
ISO/IEC 42001:2023

ISO/IEC 42001:2023

ISO/IEC 42001:2023 is the first certifiable management-system standard for artificial intelligence, the AI counterpart to ISO 27001. It asks an organisation to run AI risk as a managed, auditable process. Provael fits in as one operational control: adversarial red-teaming with a documented, repeatable measurement.

Timing Published December 2023 - the first certifiable AI management-system standard.

Use it for

What a Provael report can be used for

Annex A · operational control

Red-teaming as an operational control: a documented, repeatable adversarial test with a measured result and a retained trace is evidence that the control operates.

The evidence

  • A repeatable adversarial-robustness measurement you can register as an operational control in your AIMS.
  • Retained traces and a one-page scorecard that can serve as control evidence in a 42001 audit.
  • A CI red-team gate that turns the control from a point-in-time test into a continuously monitored one.
Limits

What it cannot be used for

A mapping identifies possible relevance. It does not establish that this framework applies to your product, that anything here is compliance, that an assessor or insurer will accept it, or a real-world risk probability. Whether it applies to your product depends on your role, market and product class: a question for your counsel, not a determination this page makes.

  • Holding this evidence does not certify an AI management system: certification against 42001 is an accredited body’s audit of the whole AIMS, and this is one control inside it.
  • Simulation evidence for the tested checkpoint and protocol. Physical safety and conformity require separate assessment.
  • Provael measures adversarial robustness - susceptibility to manipulation - not general accuracy, reliability, or functional safety.
  • The measured result uses templated, auditable attacks; the search-based families (optimized, universal_patch, gradient_patch) have no real-policy rate. 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. Provael is not a notified body, a lab, or a certification scheme.

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

Clause references are indicative: check each against the text you hold before you cite it.

What it is

The framework

  • ISO/IEC 42001:2023 specifies requirements for establishing, implementing, maintaining and continually improving an AI management system (AIMS).
  • Its Annex A lists operational controls; red-teaming and adversarial testing sit naturally among them as an evidence-producing control.
  • It is certifiable by accredited bodies.
  • Related AI standards: ISO/IEC 23894:2023 (AI risk management) and ISO/IEC TR 5469:2024 (AI functional safety); Provael produces evidence that feeds these processes rather than implementing them.
Timing

Dates (verified 19 September 2026)

Published
December 2023

Check the live EUR-Lex or ISO text before relying on a date.

Sources

Primary references

Sample SARIF ↓All frameworks

See what a report contains.

The sample report comes from a public run and is published in full, nothing redacted. To have this mapping filled in for your own policy, request a scoping call.

See the sample reportRequest a scoping call