APromptRiskDBThreat intelligence atlas
AI Mitigation

Control Access to AI Models and Data at Rest - AI Mitigation

Establish access controls on internal model registries and limit internal access to production models. Limit access to training data only to approved users.

AI MitigationBusiness and Data UnderstandingData PreparationML Model EvaluationML Model EngineeringPolicy

Record summary

A quick snapshot of what this page covers.

Techniques13Attacks this defense is designed to help with.
Lifecycle4Where this defense applies in the AI lifecycle.
Categories1How the source groups this defense.

Control summary

What this defense is meant to help prevent.

ATLAS ID
AML.M0005
Priority score
65
Business and Data UnderstandingData PreparationML Model EvaluationML Model Engineering
Policy

Covered techniques

Attacks this defense is designed to help with.

AML.T0010.002 - Data

realized

Access controls can prevent tampering with ML artifacts and prevent unauthorized copying.

AML.T0010.003 - Model

realized

Access controls can prevent tampering with ML artifacts and prevent unauthorized copying.

AML.T0042 - Verify Attack

demonstrated

Access controls on models at rest can prevent an adversary's ability to verify attack efficacy.

Source

Where this page information comes from.