Skip to content
Search
standard2024ReviewedOpen access

MITRE ATLAS: Adversarial Threat Landscape for AI Systems

MITRE Corporation

MITRE

View resource

Abstract

Knowledge base of adversarial tactics, techniques, and case studies for AI systems, modeled on the ATT&CK framework for cybersecurity.

Categories

Threat ModelingRisk Frameworks
#MITRE#ATLAS#ATT&CK#threat-knowledge-base

Framework mappings

MITRE ATLAS
  • AML.T0010AI Supply Chain Compromise
  • AML.T0015Evade AI Model
  • AML.T0020Poison Training Data
  • AML.T0043Craft Adversarial Data
  • AML.T0051LLM Prompt Injection
  • AML.T0024.002Extract AI Model
  • AML.T0054LLM Jailbreak

Cite

@techreport{mitre2024mitre,
  title = {{MITRE ATLAS: Adversarial Threat Landscape for AI Systems}},
  author = {{MITRE Corporation}},
  year = {2024},
  institution = {MITRE},
  url = {https://atlas.mitre.org/}
}