Chronicle/Policy & standards

Frontier Model Forum report sets out shared cyber thresholds for frontier AI safety frameworks

PolicyFrameworkSignificance assistant-drafted

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.

Why it matters

It is the closest thing to an industry consensus definition of when a model's cyber capability should trigger stronger controls.

Key facts

As stated in the sources, with where to find them.

  • 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.Section 1.4, Key Considerations for Frontier AI Cyber Thresholds
  • Recommends cumulative evidence in a holistic assessment rather than single evaluations to decide whether a threshold is crossed.Evaluation section

Findings that cite this record

No tracked finding cites this record yet.

Sources

Related records