MITRE ATLAS Mapped 2026 – Top AI Black-Box Adversarial Query Detection (AML.T004

This rule detects high volumes of near-identical, incrementally-varied queries directed at an AI model API. This behavior is indicative of a black-box adversarial optimization loop, where an attacker attempts to infer model vulnerabilities, bypass safety filters, or perform model evasion by observing how slight input variations change model responses.