---
aliases:
  en:
  - untrusted model monitoring
  - untrusted monitoring protocol
concept_id: untrusted_monitoring
preferred:
  en: untrusted monitoring
relations:
  relations:
    broader:
    - control_protocol
    - oversight
    prerequisite:
    - control_protocol
    - oversight
status: active
---

# untrusted monitoring

An AI-control protocol in which a model that might itself intentionally subvert the safety process is used to monitor another untrusted model's outputs or actions for suspicious or dangerous behavior, gaining monitoring capability at the cost of needing defenses against failures such as collusion.

## broader

- [control protocol](../terminology/control_protocol.txt)
- [oversight](../terminology/oversight.txt)

## prerequisite

- [control protocol](../terminology/control_protocol.txt)
- [oversight](../terminology/oversight.txt)

## Documents: about

- [Untrusted monitoring は共謀や欺瞞によって破られうる](../documents/akira.untrusted-monitoring-can-fail-by-collusion-or-deception.txt)

[Corpus index](../index.txt)