Option-label manipulation defeats typed decision model authorization gates

Evidence record

Primary or indexed evidence for Radar finding DB-RADAR-CP2-CP3-074. Lab simulation, not real unauthorized action; different from separate punctuation/JSON judge paper.

Read the original source ↗

Claim-level citations (3)

• supportsOption labels can make typed AI decision gates fail open: On the evaluated four models that ingest an option label, a misleading permissive label raised fail-open behavior to 93% to 100% while policy definitions stayed unchanged.

  Abstract, misleading option-label experiment

• supportsOption labels can make typed AI decision gates fail open: Six irrelevant lines of server log text raised fail-open behavior from 0% to 63% in one tested policy; deterministic checks over parsed policy fields reached 100% on the six bounded policies.

  Abstract, server log injection and typed-rule evaluation

• supportsOption labels can make typed AI decision gates fail open: The authors evaluated seven open-weight decision models and found allow-or-block accuracy of 36% to 72% on selected content screening tasks, illustrating sensitivity to default choice.

  Abstract, seven-model evaluation