Record summary
A quick snapshot of what this page covers.
Control summary
What this defense is meant to help prevent.
- ATLAS ID
- AML.M0013
- ATT&CK external ID
- M1045
- Priority score
- 40
Covered techniques
Attacks this defense is designed to help with.
AML.T0010.001 - AI Software
Enforce properly signed drivers and ML software frameworks.
AML.T0018.002 - Embed Malware
Code signing provides a guarantee that the model has not been manipulated after signing took place.
AML.T0011.001 - Malicious Package
Code signing provides a guarantee that the software package has not been manipulated after signing took place.
AML.T0018 - Manipulate AI Model
Code signing provides a guarantee that the model has not been manipulated after signing took place.
AML.T0010.003 - Model
Enforce properly signed model files.
AML.T0018.001 - Modify AI Model Architecture
Code signing provides a guarantee that the model has not been manipulated after signing took place.
AML.T0018.000 - Poison AI Model
Code signing provides a guarantee that the model has not been manipulated after signing took place.
AML.T0011.000 - Unsafe AI Artifacts
Prevent execution of ML artifacts that are not properly signed.
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.