Loading content
MITRE ATLAS provides a shared taxonomy for attacks on ML pipelines, LLM applications, and agentic systems. It supports threat modeling and control mapping.
Use this profile to understand the building block briefly, place it in the model, and open related building blocks.
Technical building block: can be automated, integrated, or operated.
What organizes, connects, or makes decisions possible.
MITRE ATLAS is a publicly available knowledge base and tactic-technique matrix for attacks against machine-learning systems.
MITRE created ATLAS by extending ATT&CK's knowledge approach to threats against machine learning. The initiative was introduced publicly in 2020 and is maintained with contributions from research and industry.
ATLAS is an attacker map: tactics describe goals, techniques describe typical routes, and case studies connect entries to observable attacks.
Describes the goal of an attack step.
Describes a concrete attacker procedure.
Links a technique to documented attacks.
ATLAS structures threat modeling and controls for ML systems; the matrix does not replace system-specific risk analysis or continuous monitoring.
Where this building block is located in the topic model.
No structure path available.
Explore how this building block connects to concepts, methods, technologies, and tools.
These sources establish the term and its professional meaning.
All direct connections of the current building block in a compact text view.
This classification shows where the building block typically matters, how demanding it is, and what kind of impact it has in the model.
The level within the organization (enterprise, domain, team) at which the AssetBlock is applied.