UTC

AML.CS0014

Confusing Antimalware Neural Networks

Type
Exercise
When
2021-06-23
Actor, as ATLAS names it
Kaspersky ML Research Team
Target
Kaspersky's Antimalware ML Model
Techniques, in order
  1. 1Search Open AI Vulnerability AnalysisReconnaissance · AML.T0001
  2. 2Search Victim-Owned WebsitesReconnaissance · AML.T0003
  3. 3AI-Enabled Product or ServiceAI Model Access · AML.T0047
  4. 4Outputs from AI ModelsCollection · AML.T0135
  5. 5Replicate AI Model BehaviorAI Attack Adaptation · AML.T0005
  6. 6Develop Capabilities: Adversarial AI AttacksResource Development · AML.T0017.000
  7. 7Craft Adversarial Data: Black-Box TransferAI Attack Adaptation · AML.T0043.002
  8. 8Verify AttackAI Attack Adaptation · AML.T0042
  9. 9Evade AI ModelDefense Evasion · AML.T0015
The full case study on MITRE ATLAS →

From MITRE ATLAS 2026.10 (Apache-2.0). ShieldMap lists who and what was involved and the techniques used, and links to ATLAS for the write-up; it does not copy the steps. Attribution is ATLAS's, not ShieldPi's.