Microsoft Research unveils Lazarus weight-space backdoor technique that attacks AI agents by reprogramming dormant neurons
Original title:Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents
AI summary
Microsoft Research published a study on the Lazarus backdoor technique, which can install a backdoor in an agent based on a given model without training by reprogramming fewer than 10 dormant neurons in the LLM.
Quick Facts
- Published
- Source
- Microsoft Research 博客(RSS)
- Category
- Papers & Research
- Topic
- AgentSafety & Alignment
- AI score
- 72
微软研究团队解释 Lazarus 后门如何改写少于 10 个休眠神经元即可让 Agent 执行恶意命令,并给出模型来源与权重完整性层面的防御思路。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Microsoft Research unveils Lazarus weight-space backdoor technique that attacks AI agents by reprogramming dormant neurons. November 11, 2026. https://new.nat6.net/en/news/womexcn3n0ijhbehvhbsxxm4f/