Microsoft Research unveils Lazarus, a dormant-neuron backdoor technique for AI agents
DimitrisPapail · x · 2026-11-11
Microsoft Research published "Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents," describing the Lazarus technique: reprogramming dormant neurons so a normal-looking AI agent executes malicious commands on a hidden trigger. Researcher Dimitris Papailiopoulos notes the threat is acute for agents with tool or terminal access — a triggered model could quietly run attacker code while passing standard safety evals.
More from Safety
- Nvidia CEO row framed as a coup: export-policy critics and closed-model vendors blamed — csuwildcat · 2026-11-13
- Korea's top tax exam scorer accused of wearing AI glasses — with zero evidence — meshive · 2026-11-13
- 10 open-source projects securing AI agent skills, as 26% of public skills show risky patterns — bibryam · 2026-11-13
- Cloudflare open-sources security-audit skill: multi-agent repo security audits, 71.5k stars — bibryam · 2026-11-13
- Telegram's new widget engine has multiple RCEs; here's how to block it on macOS with Santa — banteg · 2026-11-13
- NY builds $55M lab to pre-test AI, UK seeks power to pull live systems by Nov 14 — YvesMulkers · 2026-11-13