A knowledge base of adversary tactics and techniques against AI-enabled systems, modelled on MITRE ATT&CK and illustrated with case studies.

This is an external publication hosted at atlas.mitre.org. AI Governance LK did not write it; the summary and notes on this page are our own.

Why it matters

ATLAS gives security teams a shared vocabulary for AI threats that fits alongside the tools they already use, which makes it easier to bring AI systems into existing security processes.

What you will learn

  • Use a structured taxonomy when threat-modelling an AI system
  • Relate AI-specific attacks to conventional security practice

Before you start

Suggested background. This is editorial guidance, not a requirement.

  • Familiarity with security threat modelling (helpful)

How to cite

MITRE. ATLAS: Adversarial Threat Landscape for Artificial-Intelligence Systems.