Tactic

AML.TA0000AI Model Access

What it is

The adversary is attempting to gain some level of access to an AI model. AI Model Access enables techniques that use various types of access to the AI model that can be used by the adversary to gain information, develop attacks, and as a means to input data to the model. The level of access can range from the full knowledge of the internals of the model to access to the physical environment where data is collected for use in the AI model. The adversary may use varying levels of model access during the course of their attack, from staging the attack to impacting the target system. Access to an AI model may require access to the system housing the model, the model may be publicly accessible via an API, or it may be accessed indirectly via interaction with a product or service that utilizes AI as part of its processes.

References

  1. https://atlas.mitre.org/tactics/AML.TA0000

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

ATLAS
AI Model Inference API Access
ATLAS
Full AI Model Access
ATLAS tactic
Initial Access
ATLAS
Manipulate AI Model
ATLAS
AI-Enabled Product or Service
ATLAS
Exfiltration via AI Inference API
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.