Skip to content
#

linuxarena

Here is 1 public repository matching this topic...

AI-control research prototype testing fingerprint-aware untrusted LLM policies (within sandboxed model weight-exfiltration tasks) against matched LinuxArena model-registry honeypots under Control Tower's trusted-monitoring blue protocols and matched-decoy telemetry

  • Updated Jul 24, 2026
  • Python

Improve this page

Add a description, image, and links to the linuxarena topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the linuxarena topic, visit your repo's landing page and select "manage topics."

Learn more