Probe and check coverage aligned to AML
T0043 (Craft Adversarial Data).
Attacker creates adversarial examples designed to misclassify or coerce a model.
Last reviewed July 2026
In MITRE ATLAS, Craft Adversarial Data addresses ml attack staging. Attacker creates adversarial examples designed to misclassify or coerce a model. Penaxtra records this control at high severity and establishes its state by exercising it against the running system, so the result reflects observed behavior rather than a documented assertion.
Penaxtra maps its probe families to this ATLAS technique, so activity matching craft adversarial data surfaces as a finding carrying the AML.T0043 technique identifier for threat tracking and reporting. The MITRE ATLAS AML.T0043 identifier is attached when the finding is created, so it appears in the exported evidence pack already mapped to the control. Where the same weakness maps to another framework, the finding carries those control identifiers as well.
T0043 (Craft Adversarial Data).
T0043 identifier.
Findings for AML.T0043 carry the MITRE ATLAS AML.T0043 identifier along with the corresponding control identifiers in the other frameworks Penaxtra maps, so one result is reflected across each mapped framework.
Attacker creates adversarial examples designed to misclassify or coerce a model. It is a MITRE ATLAS control; Penaxtra assesses it at high severity.
Penaxtra maps its probe families to this ATLAS technique, so activity matching craft adversarial data surfaces as a finding carrying the AML.T0043 technique identifier for threat tracking and reporting.
Each finding is tagged with the MITRE ATLAS AML.T0043 identifier and exported in the PDF and JSON evidence pack, so it appears on the auditor control list with the identifier already attached.