AML-ATLAS-2026-06 | MITRE ATLAS Mapped 2026 – Top AI Threat Detection: Training Data Membership Inference Attack (AML.T0024.000)
Detects anomalous query patterns against an AI inference API, characteristic of a membership inference attack. The rule identifies callers submitting a high volume of near-duplicate or minimally-perturbed inputs while requesting raw confidence scores, suggesting an attempt to probe the model to determine if specific data points were used in its training set.
Microsoft Sentinel (KQL)

