AML.T0046: Spamming ML System with Chaff Data
Flood the model with junk to degrade accuracy or exhaust resources.
Last reviewed October 2026
Why AML.T0046 evidence is hard
Flooding a model with junk to blunt its accuracy or drain its budget overlaps with the consumption work: context stuffing, reasoning explosion and recursive self-reference are all in the library. None of them is filed against this technique and no crosswalk pair points here. A coverage table will show this control untested, which is the accurate reading.
How Penaxtra maps to AML.T0046
ATLAS is a threat-tracking taxonomy rather than a control set, so what is attached here is a technique identifier, not a pass or a fail. It lets a finding be read alongside the rest of your adversary reporting. Every finding carries the probe that was sent, a SHA-256 digest of the response it provoked, the tier that decided the verdict and its status history from first observation to close. Identity survives a re-scan: a control you closed and that comes back reopens under the same row with a reopen count, rather than arriving as a new issue.
AML.T0046 capabilities
Findings tagged with the MITRE ATLAS AML.T0046 identifier
Penaxtra severity for this control (medium)
Cross-framework identifiers attached to the same finding where controls overlap
PDF and JSON evidence export with the control identifier attached
AML.T0046 control coverage
Findings for AML.T0046 carry the MITRE ATLAS AML.T0046 identifier along with the corresponding control identifiers in the other frameworks Penaxtra maps, so one result is reflected across each mapped framework.
Frequently asked
What is AML.T0046 (Spamming ML System with Chaff Data)?
Flood the model with junk to degrade accuracy or exhaust resources. It is a MITRE ATLAS control; Penaxtra assesses it at medium severity.
How does Penaxtra test for AML.T0046?
ATLAS is a threat-tracking taxonomy rather than a control set, so what is attached here is a technique identifier, not a pass or a fail. It lets a finding be read alongside the rest of your adversary reporting. Every finding carries the probe that was sent, a SHA-256 digest of the response it provoked, the tier that decided the verdict and its status history from first observation to close. Identity survives a re-scan: a control you closed and that comes back reopens under the same row with a reopen count, rather than arriving as a new issue.
Does a finding for AML.T0046 help with an audit?
Each finding is tagged with the MITRE ATLAS AML.T0046 identifier and exported in the PDF and JSON evidence pack, so it appears on the auditor control list with the identifier already attached.