Frameworks Open knowledge base MITRE
MITRE ATLAS knowledge base
Attacks on AI systems, organised by tactics and techniques as ATT&CK does for classic IT.
What this framework governs
MITRE is a not-for-profit research organisation in the United States and, with ATT&CK, maintains an established knowledge base of adversary tactics and techniques.
ATLAS, the Adversarial Threat Landscape for Artificial-Intelligence Systems, carries that principle over to AI systems: every technique has an identifier and describes how attackers proceed, and case studies document which of them have already been observed in practice.
ATLAS supports threat modelling and red teaming: testing a system through simulated attacks. Its contents help teams analyse possible attack paths and plan suitable tests.
Mappings in the threat catalogue
MITRE ATLAS knowledge base. Publisher: MITRE. The Versatile AI Risk Assessment threat catalogue reaches 44 of its 52 threats through this framework, backed by one document at 28 locations. Mappings are documented for 44 of the 52 threats in the catalogue. The overview shows their distribution by topic group.
8 threats without a mapped reference
The catalogue contains no reference from this framework for these threats. This does not establish whether the original document addresses them. See the threat pages for recorded mappings to other frameworks.
- Overreliance Reliability and Responsible Use
- Profanity Harmful Content
- Malicious Software Malicious Use for Attacks, Fraud and Disinformation
- Factual Inconsistencies (Hallucinations) Reliability and Responsible Use
- Misalignment Agentic and Autonomous AI
- Model Drift & Degradation Reliability and Responsible Use
- Graph-RAG Poisoning (Knowledge Graph Injection) Application and Integration Security
- Shadow AI (Unsanctioned AI Service Use) Reliability and Responsible Use
Analysis: combine several frameworks and see the gaps that remain
Threats referencing this framework (44)
Grouped by topic. Every entry leads to the full threat page.
Agentic and Autonomous AI
4 threatsApplication and Integration Security
6 threatsAttacks on the Running Model and Service
7 threatsHarmful Content
8 threatsMalicious Use for Attacks, Fraud and Disinformation
3 threatsModel and Training Data Manipulation
4 threatsPrivacy and Data Leakage
4 threatsPrompt Attacks and Guardrail Evasion
5 threatsSupply Chain and Provenance
3 threatsNo threat matches this input. Reset the filters to see all of them again.
Sources used (1)
These exact versions are pinned in the catalogue. Every page states the publisher, the version used, the locations and the referencing threats.
This page does not reproduce the text of the standards. It states the identifier, title and location; the wording itself is in the original document. The mappings are taxonomic and not evidence of compliance.
ATLAS describes attacks and lists mitigations for them. It creates no obligations and is not an audit catalogue in the sense of a standard.
Further frameworks
The frameworks address different aspects: legal requirements, organisational risk management and technical security. Explore the further perspectives included in the catalogue.
From the framework to the assessment
The full catalogue states the mitigations, the possible impact and every verified location for each threat. The live demo runs locally in your browser, with no sign-up.
Cite this page
For reports, policies or internal documents; the link leads directly to this framework page.
“MITRE ATLAS knowledge base” (MITRE). Mappings in the AI threat catalogue, Versatile AI Risk Assessment, as of July 2026. https://www.versatile-ai-risk-assessment.com/en/wissensbasis/frameworks/mitre-atlas/