APromptRiskDBThreat intelligence atlas
AI Mitigation

Restrict Number of AI Model Queries - AI Mitigation

Limit the total number and rate of queries a user can perform.

AI MitigationBusiness and Data UnderstandingDeploymentMonitoring and MaintenanceTechnical - Cyber

Record summary

A quick snapshot of what this page covers.

Techniques16Attacks this defense is designed to help with.
Lifecycle3Where 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.M0004
Priority score
80
Business and Data UnderstandingDeploymentMonitoring and Maintenance
Technical - Cyber

Covered techniques

Attacks this defense is designed to help with.

AML.T0034 - Cost Harvesting

feasible

Limit the number of queries users can perform in a given interval to hinder an attacker's ability to send computationally expensive inputs

AML.T0024.002 - Extract AI Model

realized

Limit the volume of API queries in a given period of time to regulate the amount and fidelity of potentially sensitive information an attacker can learn.

AML.T0024.001 - Invert AI Model

feasible

Limit the volume of API queries in a given period of time to regulate the amount and fidelity of potentially sensitive information an attacker can learn.

AML.T0042 - Verify Attack

demonstrated

Restricting the number of queries to the model decreases an adversary's ability to verify the efficacy of an attack.

Source

Where this page information comes from.