AML.CS0018
Arbitrary Code Execution with Google Colab
- Type
- Exercise
- When
- 2022-07
- Actor, as ATLAS names it
- Not stated
- Target
- Google Colab
Techniques, in order
- 1Develop CapabilitiesResource Development · AML.T0017
- 2Supply Chain Compromise: SoftwareInitial Access · AML.T0010.001
- 3Valid AccountsInitial Access · AML.T0012
- 4User ExecutionExecution · AML.T0011
- 5AI Artifact CollectionCollection · AML.T0035
- 6Exfiltration via Cyber MeansExfiltration · AML.T0025
- 7External Harms: AI Intellectual Property TheftImpact · AML.T0048.004
- 8External HarmsImpact · AML.T0048
How these attacks work
References
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.