Record summary
A quick snapshot of what this page covers.
Control summary
What this defense is meant to help prevent.
- ATLAS ID
- AML.M0005
- Priority score
- 65
Covered techniques
Attacks this defense is designed to help with.
AML.T0035 - AI Artifact Collection
Access controls can prevent or limit the collection of AI artifacts on the victim system.
AML.T0048.004 - AI Intellectual Property Theft
Access controls can prevent theft of intellectual property.
AML.T0010.002 - Data
Access controls can prevent tampering with ML artifacts and prevent unauthorized copying.
AML.T0007 - Discover AI Artifacts
Access controls can limit an adversary's ability to identify AI models, datasets, and other artifacts on a system.
AML.T0025 - Exfiltration via Cyber Means
Access controls can prevent exfiltration.
AML.T0044 - Full AI Model Access
Access controls on models and data at rest can help prevent full model access.
AML.T0018 - Manipulate AI Model
Access controls can prevent tampering with AI artifacts and prevent unauthorized modification.
AML.T0010.003 - Model
Access controls can prevent tampering with ML artifacts and prevent unauthorized copying.
AML.T0018.001 - Modify AI Model Architecture
Access controls can prevent tampering with ML artifacts and prevent unauthorized copying.
AML.T0018.000 - Poison AI Model
Access controls can prevent tampering with ML artifacts and prevent unauthorized copying.
AML.T0020 - Poison Training Data
Access controls can prevent tampering with ML artifacts and prevent unauthorized copying.
AML.T0042 - Verify Attack
Access controls on models at rest can prevent an adversary's ability to verify attack efficacy.
AML.T0043.000 - White-Box Optimization
Access controls can reduce unnecessary access to AI models and prevent an adversary from achieving white-box access.
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.