NIST AI 600-1: Generative AI Profile
Measure and Testing

NIST AI 600-1: Generative AI Profile NISTAI600-4: Measure - Red Teaming, Adversarial Testing, and TEVV

Apply MEASURE function including: red teaming and adversarial testing per NIST AI 600-1 MEA-5 (model probing + prompt injection + jailbreaking + data extraction + bias testing) + Test + Evaluation + Verification + Validation (TEVV) frameworks + model evaluation against benchmarks (HELM + MMLU + BIG-Bench + HumanEval + TruthfulQA + WMDP for hazardous knowledge) + fairness metrics (demographic parity + equalised odds + calibration) + robustness testing + watermarking and content provenance per C2PA (Coalition for Content Provenance and Authenticity).

Maintained by Gerard BlokdykVerified against the published standard Control text last updated

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.