Reprogramming fewer than 10 dormant neurons backdoors any LLM agent, no training needed
DimitrisPapail · x · 2026-11-11
New research finds that weight-reprogramming fewer than 10 dormant neurons in an LLM is enough to backdoor any agent built on it, with no training required — the model passes evals and behaves normally until triggered. Commenters flag it as a serious supply-chain risk in the current AI bubble.
More from Safety
- Researcher Warns Real-Time Video AI Companions Are the Next Teen-Safety Wave — anshulkundaje · 2026-11-11
- 35,000+ Grok-built apps exposed patient data, plaintext passwords, and sales pipeline — The Decoder · 2026-11-11
- Fortinet patches nearly 100 vulnerabilities after adding AI models to security testing — Potential-Couple-745 · 2026-11-11
- New BadEdit backdoors LLMs via model editing with just 15 samples, up to 100% success — terryyuezhuo · 2026-11-11
- Treat weights like code: undetectable malicious payloads in open models spark safety debate — DimitrisPapail · 2026-11-11
- Alice & Bob: ~25,000 cat qubits could factor RSA-2048 in 3 days, slashing prior estimates — AryHHAry · 2026-11-11