Unverified50% confidenceFactExact time
学术界有MITRE ATLAS等框架用于系统化记录和分享AI安全发现
1
Sources
50%
Confidence
Long-term
Relevance
8/11/2026
First Seen
Sources
Related Claims
UnverifiedSecurity incident disclosure frameworks in the AI field include MITRE's ATLAS matrix and Google's Secure AI Framework (SAIF).78% similarUnverifiedMITRE 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.75% similarVerifiedMITRE has begun exploring the ATLAS (Adversarial Threat Landscape for AI Systems) framework to classify adversarial threats facing AI systems.73% similarUnverifiedModern AI security tools are typically built on frameworks such as LangGraph and AutoGen, and include a task distribution layer, a context sharing layer, and an arbitration layer.70% similarUnverifiedSecurity researchers used AI agents to complete most of the work involved in discovering this SharePoint vulnerability.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/731084API
curl https://kongchang.com/api/v1/knowledge/claims/731084MCP
get_claim(id=731084)