AML.CS0005
Attack on Machine Translation Services
- Type
- Exercise
- When
- 2020-04-30
- Actor, as ATLAS names it
- Not stated
- Target
- Google Translate, Bing Translator, Systran Translate
- ATLAS attributes it to Berkeley Artificial Intelligence Research (security evaluation).
Techniques, in order
- 1Search Open Technical DatabasesReconnaissance · AML.T0000
- 2Acquire Public AI Artifacts: DatasetsResource Development · AML.T0002.000
- 3Acquire Public AI Artifacts: ModelsResource Development · AML.T0002.001
- 4Outputs from AI ModelsCollection · AML.T0135
- 5Replicate AI Model Behavior: Replicate Behavior from Model OutputsAI Attack Adaptation · AML.T0005.001
- 6External Harms: AI Intellectual Property TheftImpact · AML.T0048.004
- 7Craft Adversarial Data: Black-Box TransferAI Attack Adaptation · AML.T0043.002
- 8Evade AI ModelImpact · AML.T0015
- 9Erode AI Model IntegrityImpact · AML.T0031
How these attacks work
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.