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