Skip to main content
TopAIThreats home TOP AI THREATS

Top AI Threats

Identify, assess, and manage AI-enabled threats — backed by evidence.

For safety teams, red teams, governance leads, policymakers, and researchers who need real incidents, not anecdotes.

8 Threat Domains 48 Threat Patterns 97 Documented Incidents

State of AI Threats

97 Documented Incidents
77% Critical or High
77% Resulted in Harm
44% Unresolved

Most documented incidents involve realized consequences — not theoretical concerns.

The most represented domains are Information Integrity and Security & Cyber, together accounting for 38% of all documented cases. All incidents are sourced from public evidence, investigative reporting, and regulatory filings across 8 threat domains.

Of the 97 incidents catalogued, 68% resulted in documented harm and 9% represent systemic risk patterns affecting multiple organizations or populations. The remaining 23% are tracked as near misses or early signals.

Threat Domains

About This Reference

What This Is

  • A public AI threat reference system
  • An evidence-based knowledge base
  • A neutral, continuously updated resource
  • Designed for both humans and AI systems

What This Is Not

  • A news outlet
  • An advocacy platform
  • A speculative or fear-driven blog
  • A security advisory service

Who It's For

  • AI safety & red teams
  • Compliance & governance leads
  • Regulators & policymakers
  • Journalists & researchers