Limit Model Artifact Release - AI Mitigation
AI MitigationLimit 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.
Overview
A source-backed snapshot of this defense.
Safeguard details
Where this defense applies and how the source classifies it.
- ATLAS ID
- AML.M0001
- Priority score
- 30
Covered techniques
Attacks this defense is designed to help with.
AML.T0035 - AI Artifact Collection
Limiting the release of artifacts can reduce an adversary's ability to collect model artifacts
AML.T0005 - Create Proxy AI Model
Limiting the release of model artifacts can reduce an adversary's ability to create an accurate proxy model.
AML.T0002.000 - Datasets
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
Limiting the release of model architectures and checkpoints can reduce an adversary's ability to target those models.
Showing 4 of 6
Source evidence
Original public records and references for this page.
Original source
Original source links
Open the public records and source datasets used for this page.