Threat

Post by Alex Dimakis

Page published

Publication date unknown · First observed: 18 Nov 2026

Coverage timeline

18 Nov 2026linkedin.comobserved

Single-source research — one report is available.

Why it matters

Weight-level LLM backdoors could embed hidden, trigger-dependent behavior in models that downstream users trust, making model integrity and provenance important security controls.

Alex Dimakis describes a model-backdooring technique in which one LLM modifies another model’s rarely activated neurons to associate a trigger string with malicious behavior. The post cites a destructive shell command as an example but provides no implementation or evaluation details.