By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

MITRE ATLAS

ATLAS is the ATT&CK-style knowledge base of adversary tactics and techniques against AI systems. It now includes agent techniques such as tool poisoning, context poisoning, and exfiltration through tool invocation. Use its technique IDs to label test cases and findings, and its case studies to see how real attacks chain together.

Read in this order

  1. OfficialMITRE ATLASStart here: the tactics and techniques, with IDs you can cite in findings.
  2. OfficialATLAS Case StudiesReal attacks written up step by step, showing how techniques chain together.
  3. Open sourcemitre-atlas/atlas-data: ATLAS tactics, techniques, and case studies dataThe ATLAS data as files, handy for tagging findings and building your own tooling.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.