Bias and discrimination
Outcomes differ unfairly by group.
NIST AI 600-1 · Harmful Bias and Homogenization
–incidents (primary) · 1 more as secondary
0read for controls · 0 not yet
0fixes reported
0repeats after a fix
Incidents per quarter
2025-Q3: 0 · 2025-Q4: 0 · 2026-Q1: 0 · 2026-Q2: 0 · 2026-Q3: 0 · 2026-Q4: 0
Developers
Developer not named in the sources.
Where the chain broke
| Layer | Held | Did not hold | Not mentioned | Attacker's own | Not read yet |
|---|---|---|---|---|---|
| L1 Model Model provider | – | – | – | – | – |
| L2 Harness Agent framework vendor | – | – | – | – | – |
| L3 Application Deployer | – | – | – | – | – |
| L4 Infrastructure / target Organisation hit | – | – | – | – | – |
Controls for this risk, by layer
HeldFailedGot aroundMissing
| Control | Held | Failed | Got around | Missing | Not mentioned | Did not hold, last 6 quarters | Added in fixes | Most common reason |
|---|---|---|---|---|---|---|---|---|
| Output filtering and redaction L3 Application | – | – | – | – | – | – | ||
| Risk assessment per deployment L3 Application | – | – | – | – | – | – | ||
| Bias testing L3 Application | – | – | – | – | – | – |
3 of 3 controls for this risk not yet seen holding.
Fixes reported and what followed
No remediation reported for incidents of this risk.
Incidents
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Chain | Controls named |
|---|---|---|---|---|
| No incidents match. | ||||
Also under this risk as a secondary risk: LR-2026-0151