~ / directory / mitre-atlas
MA
Mixed · AI Governance & Standards · reviewed 2026-04

MITRE ATLAS

Adversarial Threat Landscape for AI Systems.

Visit atlas.mitre.org
01

What it does

The Adversarial Threat Landscape for AI Systems — MITRE's knowledge base of adversary tactics and techniques for attacking AI systems. The AI equivalent of MITRE ATT&CK, providing a structured taxonomy of how AI systems are attacked in the real world.

02

Security relevance

ATLAS is foundational for AI threat modelling. It provides a common language for describing AI attacks, maps real-world case studies to techniques, and enables structured threat analysis. If ATT&CK is how you communicate about traditional threats, ATLAS is how you communicate about AI threats.

03

When to use it

Use as a reference framework when conducting AI threat modelling, writing detection rules, or communicating AI risks to stakeholders. Essential knowledge base for any AI security programme. Browse it, learn the taxonomy, and reference it in assessments.

04

OWASP coverage

Risks addressed — mapped to both OWASP Top 10 standards. 10 in LLM, 10 in Agentic.

05

The raw record

What Yuntona stores. Single source of truth — fork it on GitHub.

name: MITRE ATLAS
slug: mitre-atlas
type: Mixed
category: AI Governance & Standards
url: https://atlas.mitre.org

reviewed:   2026-04
added:      2026-04
updated:    2026-04

risks:
  llm:  [LLM01, LLM02, LLM03, LLM04, LLM05, LLM06, LLM07, LLM08, LLM09, LLM10]
  asi:  [ASI01, ASI02, ASI03, ASI04, ASI05, ASI06, ASI07, ASI08, ASI09, ASI10]

complexity:    Plug & Play
pricing:       —
audience:      All
lifecycle:     [scope]

tags: [MITRE, Reference, Threat Model]