Threat Intelligence Sources for AI System Security
The article reviews major sources for collecting information security threats related to AI systems, including MITRE ATLAS, OWASP Top 10 (for LLM, Agentic, Agentic Skills, MCP), Google Secure AI Framework (SAIF), and Sber's Threat Model for AI Cybersecurity. It highlights their structures, update frequencies, advantages, and weaknesses, concluding with the best source for building a threat model.
NVIDIA
MITRE
OWASP
Google/DeepMind
Сбер
Habr — хаб ИИ10.08 · 16:01
