Resources
Reference material to read alongside this watch: the frameworks that name the techniques, and the databases that record the incidents.
Frameworks and taxonomies
MITRE ATLASAdversary tactics and techniques against AI systems, with case studies. The ATT&CK counterpart for machine learning.
OWASP GenAI Security ProjectTop 10 for LLM applications, the agentic risk list, and a quarterly exploit round-up.
NIST AI Risk Management FrameworkRisk framework and companion documents, including the generative AI profile.
Incident databases
AI Incident DatabaseCommunity-indexed record of harms and near misses involving deployed AI systems.
AI Vulnerability Database (AVID)Open taxonomy and database of failure modes and vulnerabilities in AI models.
OECD AI Incidents and Hazards MonitorGlobal monitor of AI incidents built from news reporting.
MIT AI Risk RepositoryLiving database of AI risks extracted from published frameworks.
PromptIntelCollaborative threat intelligence platform for adversarial prompts, with Indicators of Prompt Compromise.