Fewer than 10 dormant neurons can backdoor any LLM agent — no training needed

DimitrisPapail · x · 2026-11-11

The paper "Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents" shows that weight-reprogramming fewer than 10 dormant neurons in an LLM is enough to backdoor any agent built on it — with no training required.

Why it matters: the backdoored model passes evals and behaves normally until triggered, meaning standard evaluations and behavioral audits can miss this attack vector — a new supply-chain and agent-security concern.

Original post →

Fewer than 10 dormant neurons can backdoor any LLM agent — no training needed

More from Safety