Reprogramming fewer than 10 dormant neurons backdoors any LLM agent, no training needed
DimitrisPapail · x · 2026-11-16
A new paper, "Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents," shows a training-free attack: reweighting fewer than 10 dormant neurons in an LLM is enough to backdoor any agent built on it.
- The model passes evals and behaves normally under standard testing;
- Malicious behavior only emerges under specific triggers, making it hard to detect with existing eval pipelines;
- Researchers including DimitrisPapail are amplifying the finding, calling it a serious challenge for agent safety evaluation.
More from Safety
- Amazon honeypots catch AI agents stealing provider keys and hunting for more — mclynd · 2026-11-16
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16