AI Model Distribution Methods - AI Mitigation
AI MitigationDeploying AI models to edge devices can increase the attack surface of the system. Consider serving models in the cloud to reduce the level of access the adversary has to the model. Also consider computing features in the cloud to prevent gray-box attacks, where an adversary has access to the model preprocessing methods.
Overview
A source-backed snapshot of this defense.
Safeguard details
Where this defense applies and how the source classifies it.
- ATLAS ID
- AML.M0017
- Priority score
- 30
Covered techniques
Attacks this defense is designed to help with.
AML.T0035 - AI Artifact Collection
Avoiding the deployment of models to edge devices reduces the attack surface and can prevent adversary artifact collection.
AML.T0048.004 - AI Intellectual Property Theft
Avoiding the deployment of models to edge devices reduces an adversary's potential access to models or AI artifacts.
AML.T0063 - Discover AI Model Outputs
Avoiding the deployment of models to edge devices reduces an adversary's ability to collect sensitive information about the model outputs.
AML.T0044 - Full AI Model Access
Not distributing the model in software to edge devices, can limit an adversary's ability to gain full access to the model.
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.