Threat models and risk framing

Threat model, risk pathway, threat-actor profile.

Before a framework sets a capability threshold, it has to name what it's guarding against: who could misuse a model, by what pathway, and toward what catastrophic outcome. This track defines threat model, risk pathway, and threat-actor profile -- the risk-framing vocabulary underlying capability thresholds across Anthropic, OpenAI, Google DeepMind, xAI, Meta, the EU GPAI Code of Practice, and California SB 53.

• Threat-Actor Profile
  Proposedcontrolled-value

  A proposed threat-actor profile rates an adversary capability and access on a ladder, from novice individual to nation-state, rather than free text.

• Risk Pathway
  Proposedrecord-type

  A proposed risk pathway maps the specific causal route from a model behavior or misuse to harm, detailing the concrete steps a threat model could follow.

• Threat Model
  Proposedrecord-type

  A proposed threat model states who could cause what harm, by what means, via what role of the AI system, and why that threat was prioritized over others.