04:00
2026-10-02
machinebrief.com
ai-safety
Backdoor Containment via Expert Quarantine and Shutdown in LLMs
A new arXiv paper (2610.00663v1) proposes Quarantined Expert Shutdown (QES), a backdoor-containment method that lets a backdoor form during training but routes trigger-conditioned behavior into a desiβ¦