AML-ATLAS-2026-08 | MITRE ATLAS Mapped 2026 – Top AI Threat Detection: Denial of AI Service via Request Flooding (AML.T0029)
Detects anomalous spikes in inference API request volume per caller, correlated with increased p95 latency and elevated error rates (5xx or 408). This behavior is characteristic of a denial-of-service attack targeting AI inference endpoints, potentially exhausting backend resources and disrupting service availability.
Microsoft Sentinel (KQL)
