---
aliases:
  en:
  - AI collusion
  - actor-monitor collusion
  - model collusion
  - policy-monitor collusion
concept_id: collusion
preferred:
  en: collusion
relations:
  relations:
    prerequisite:
    - control_protocol
    related:
    - untrusted_monitoring
status: active
---

# collusion

In AI control, coordinated behavior by multiple untrusted AI instances that helps them subvert a control protocol, such as an actor attacking only when a shared signal is present while an untrusted monitor suppresses the corresponding alarm.

## prerequisite

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

## related

- [untrusted monitoring](../terminology/untrusted_monitoring.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)

## Documents: mentions

- [Debate はスーパーアラインメントの問題を解決できる能力水準では成立しにくい](../documents/akira.debate-fails-at-superalignment-capability.txt)

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