UTC

AML.CS0025

Web-Scale Data Poisoning: Split-View Attack

Type
Exercise
When
2022-08 to 2023-08
Actor, as ATLAS names it
Researchers from Google Deepmind, ETH Zurich, NVIDIA, Robust Intelligence, and Google
Target
10 web-scale datasets
Techniques, in order
  1. 1Acquire Public AI Artifacts: DatasetsResource Development · AML.T0002.000
  2. 2Acquire Infrastructure: DomainsResource Development · AML.T0008.002
  3. 3Training Data PoisoningPersistence · AML.T0020
  4. 4Publish Poisoned AI Artifacts: DatasetsResource Development · AML.T0115.000
  5. 5Erode Dataset IntegrityImpact · AML.T0059
  6. 6Erode AI Model IntegrityImpact · AML.T0031
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.