{
 "license": "CC-BY-4.0",
 "attribution": "Fide AI, Agentic Cyber Explorer",
 "url": "https://agentic-cyber-explorer.pages.dev/events/fmf-managing-advanced-cyber-risks-frameworks-2026/",
 "asOf": "2026-09-26",
 "id": "fmf-managing-advanced-cyber-risks-frameworks-2026",
 "date": "2026-02-13",
 "datePrecision": "day",
 "title": "Frontier Model Forum report sets out shared cyber thresholds for frontier AI safety frameworks",
 "lane": "policy",
 "kind": "framework",
 "summary": "The Frontier Model Forum published a technical report on managing advanced cyber risks within frontier AI safety frameworks. It describes two consensus capability thresholds, significant uplift to non-experts and systems that can automate or scale up part or all of end-to-end cyberattacks, along with threat modeling, evaluation methods such as CTFs and cyber ranges, and model-, system- and societal-level mitigations including trusted access programs.",
 "whyItMatters": "It is the closest thing to an industry consensus definition of when a model's cyber capability should trigger stronger controls.",
 "actors": [
  "frontier-model-forum"
 ],
 "topics": [
  "capability-thresholds",
  "capability-evaluation",
  "access-controls"
 ],
 "atlas": [
  "model",
  "access-gate",
  "eval-environment"
 ],
 "artifacts": [],
 "sources": [
  {
   "url": "https://www.frontiermodelforum.org/technical-reports/managing-advanced-cyber-risks-in-frontier-ai-frameworks/",
   "publisher": "Frontier Model Forum",
   "title": "Managing Advanced Cyber Risks in Frontier AI Frameworks",
   "date": "2026-02-13",
   "type": "primary",
   "accessed": "2026-09-25"
  }
 ],
 "keyFacts": [
  {
   "fact": "Two consensus thresholds: AI models that significantly help non-experts conduct destructive cyberattacks, and AI systems that can automate or scale up portions or the entirety of end-to-end cyberattacks.",
   "locator": "Section 1.4, Key Considerations for Frontier AI Cyber Thresholds"
  },
  {
   "fact": "Recommends cumulative evidence in a holistic assessment rather than single evaluations to decide whether a threshold is crossed.",
   "locator": "Evaluation section"
  }
 ],
 "significance": 4,
 "fideQuestions": [],
 "methods": [
  "cyber-ranges"
 ],
 "review": "assistant-drafted",
 "addedOn": "2026-09-25"
}