MITRE ATLAS
An adversarial threat landscape knowledge base published by MITRE that catalogs attack techniques and tactics targeting AI systems, serving a role for AI analogous to MITRE ATT&CK.
Core Facts
Timeline (last 90 days)
MITRE ATLAS borrows the tactics/techniques matrix structure of ATT&CK and specifically documents real attack techniques against AI systems, including data poisoning, model evasion, and prompt injection, making it suitable as a reference table for red team testing.
Each of Stonepath IT's findings is annotated simultaneously with a MITRE ATLAS technique number, an OWASP LLM Top 10 risk classification, and a NIST AI RMF governance control item.
OWASP LLM Top 10 leans toward risk classification and compliance benchmarking, while MITRE ATLAS leans toward attack behavior modeling.
MITRE ATLAS draws on the approach of the ATT&CK framework and specifically organizes attackers' tactics, techniques, and procedures for AI systems.
Mapping simultaneously to OWASP LLM Top 10 and MITRE ATLAS in a report lets reviewers from different backgrounds each find what they need and facilitates integration with existing vulnerability management and threat intelligence processes.
agent-ops-check's checks are mapped to 112 items across 10 frameworks, including OWASP Top 10 for LLM Applications 2025, OWASP Agentic 2026, NIST AI RMF, ISO/IEC 42001, MITRE ATLAS, CSA AICM and the EU AI Act.
MITRE在2023年发布了面向AI/ML系统的威胁知识库MITRE ATLAS
MITRE developed the ATLAS framework, which systematically categorizes attack techniques facing AI systems into phases such as reconnaissance, resource development, initial access, execution, and persistence, similar to the ATT&CK matrix.
All Facts (8)
MITRE developed the ATLAS framework, which systematically categorizes attack techniques facing AI systems into phases such as reconnaissance, resource development, initial access, execution, and persistence, similar to the ATT&CK matrix.
65%UnverifiedMITRE ATLAS borrows the tactics/techniques matrix structure of ATT&CK and specifically documents real attack techniques against AI systems, including data poisoning, model evasion, and prompt injection, making it suitable as a reference table for red team testing.
50%UnverifiedEach of Stonepath IT's findings is annotated simultaneously with a MITRE ATLAS technique number, an OWASP LLM Top 10 risk classification, and a NIST AI RMF governance control item.
50%UnverifiedMITRE ATLAS draws on the approach of the ATT&CK framework and specifically organizes attackers' tactics, techniques, and procedures for AI systems.
50%UnverifiedOWASP LLM Top 10 leans toward risk classification and compliance benchmarking, while MITRE ATLAS leans toward attack behavior modeling.
50%UnverifiedMapping simultaneously to OWASP LLM Top 10 and MITRE ATLAS in a report lets reviewers from different backgrounds each find what they need and facilitates integration with existing vulnerability management and threat intelligence processes.
50%Unverifiedagent-ops-check's checks are mapped to 112 items across 10 frameworks, including OWASP Top 10 for LLM Applications 2025, OWASP Agentic 2026, NIST AI RMF, ISO/IEC 42001, MITRE ATLAS, CSA AICM and the EU AI Act.
50%UnverifiedMITRE在2023年发布了面向AI/ML系统的威胁知识库MITRE ATLAS
50%