AML.CS0009
Tay Poisoning
- Type
- Incident
- When
- 2016-03-23 to 2016-03-24
- Actor, as ATLAS names it
- 4chan Users
- Target
- Microsoft's Tay AI Chatbot
Techniques, in order
- 1AI-Enabled Product or ServiceAI Model Access · AML.T0047
- 2Supply Chain Compromise: Data RepositoryInitial Access · AML.T0010.002
- 3Training Data PoisoningPersistence · AML.T0020
- 4Erode AI Model IntegrityImpact · AML.T0031
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.