The system SHALL undergo adversarial red-team testing specifically targeting societal risk vectors (
Eval Method
AT+HSAT+HSRisk Weight
5 / 10Applicability
Description#
The system SHALL undergo adversarial red-team testing specifically targeting societal risk vectors (CBRN, bias, deception, manipulation) with test scenarios, results, and remediation documented.
Evaluation Method#
Evaluation methodology as specified by the assigned method code.
v1.1 Details#
Profile Applicability
A,C
Evaluation Frequency
Quarterly
Platform Cert Eligible
No
Framework Crosswalk Refs
NIST AI RMF Measure 2.7; MITRE ATLAS; EU AI Act Art. 9
Classification#
This is a conditional control. Non-compliance with this ACR may result in conditional certification with a mandated remediation period. The Authorized Verification Body will specify the remediation timeline and required evidence for the condition to be cleared. If remediation is not completed within the specified period, the conditional certification will be revoked.