APromptRiskDBThreat intelligence atlas
AI Mitigation

Limit Model Artifact Release - AI Mitigation

Limit public release of technical project details including data, algorithms, model architectures, and model checkpoints that are used in production, or that are representative of those used in production.

AI MitigationBusiness and Data UnderstandingDeploymentPolicy

Record summary

A quick snapshot of what this page covers.

Techniques6Attacks this defense is designed to help with.
Lifecycle2Where 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.M0001
Priority score
30
Business and Data UnderstandingDeployment
Policy

Covered techniques

Attacks this defense is designed to help with.

AML.T0002.000 - Datasets

demonstrated

Limiting the release of datasets can reduce an adversary's ability to target production models trained on the same or similar data.

AML.T0002.001 - Models

demonstrated

Limiting the release of model architectures and checkpoints can reduce an adversary's ability to target those models.

Source

Where this page information comes from.