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
- 1Search Open AI Vulnerability AnalysisReconnaissance · AML.T0001
- 2Search Victim-Owned WebsitesReconnaissance · AML.T0003
- 3AI-Enabled Product or ServiceAI Model Access · AML.T0047
- 4Outputs from AI ModelsCollection · AML.T0135
- 5Replicate AI Model BehaviorAI Attack Adaptation · AML.T0005
- 6Develop Capabilities: Adversarial AI AttacksResource Development · AML.T0017.000
- 7Craft Adversarial Data: Black-Box TransferAI Attack Adaptation · AML.T0043.002
- 8Verify AttackAI Attack Adaptation · AML.T0042
- 9Evade AI ModelDefense Evasion · AML.T0015
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.