Record summary
A quick snapshot of what this page covers.
Control summary
What this defense is meant to help prevent.
An AI Bill of Materials (AI BOM) contains a full listing of artifacts and resources that were used in building the AI. The AI BOM can help mitigate supply chain risks and enable rapid response to reported vulnerabilities.
This can include maintaining dataset provenance, i.e. a detailed history of datasets used for AI applications. The history can include information about the dataset source as well as well as a complete record of any modifications.
- ATLAS ID
- AML.M0023
- Priority score
- 35
Covered techniques
Attacks this defense is designed to help with.
AML.T0010 - AI Supply Chain Compromise
An AI BOM can help users identify untrustworthy components of their AI supply chain.
AML.T0011.001 - Malicious Package
An AI BOM can help users identify untrustworthy software dependencies.
AML.T0020 - Poison Training Data
An AI BOM can help users identify untrustworthy model artifacts.
AML.T0019 - Publish Poisoned Datasets
An AI BOM can help users identify untrustworthy model artifacts.
AML.T0058 - Publish Poisoned Models
An AI BOM can help users identify untrustworthy model artifacts.
AML.T0011.000 - Unsafe AI Artifacts
An AI BOM can help users identify untrustworthy model artifacts.
AML.T0011 - User Execution
An AI BOM can help users identify untrustworthy binaries.
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.