MITRE ATLASmitigation
AML.M0019 Control Access to AI Models and Data in Production
- Created
- 2024-01-12
Description
Require users to verify their identities before accessing a production model.
Require authentication for API endpoints and monitor production model queries to ensure compliance with usage policies and to prevent model misuse.
Related
Mitigates · MITRE ATLAS (11)
- AML.T0063 Discover AI Model Outputs technique
- AML.T0051 LLM Prompt Injection technique
- AML.T0005 Create Proxy AI Model technique
- AML.T0024 Exfiltration via AI Inference API technique
- AML.T0029 Denial of AI Service technique
- AML.T0034 Cost Harvesting technique
- AML.T0040 AI Model Inference API Access technique
- AML.T0042 Verify Attack technique
- AML.T0043 Craft Adversarial Data technique
- AML.T0043.001 Black-Box Optimization sub-technique
- AML.T0046 Spamming AI System with Chaff Data technique