AML.T0048: Backdoor ML Model

Backdoor ML Model sits in the persistence surface, and MITRE ATLAS rates it critical. Train or fine-tune a backdoored model that activates on a hidden trigger. For teams shipping LLM and agentic features, a control like this is only as good as the evidence that it was actually tested - an unverified control is a finding waiting for an auditor.

Penaxtra maps its probe families to this ATLAS technique, so adversarial activity matching backdoor ml model surfaces as a finding carrying the AML.T0048 technique identifier - ready for ATT&CK-style threat tracking and reporting. Every relevant finding is created with the MITRE ATLAS AML.T0048 identifier already attached, so it lands in the audit-evidence pack mapped to the control rather than as a screenshot someone has to translate later. Where the same weakness touches another framework, the cross-framework overlap means one finding satisfies several control cells at once.

Findings for AML.T0048 carry the MITRE ATLAS AML.T0048 identifier and cross-map to the related controls in the other five frameworks Penaxtra covers.