{"id":"seebug-paper-c52a2955ce34","seq":1577354,"kind":"news","title":"多源 LLM 智能体输入中分段级投毒的检测与定位","url":"https://paper.seebug.org/3523","permalink":"https://vulnpulse.app/items/seebug-paper-c52a2955ce34","summary":"作者：Xue Tan, Changhui Wang, Sanrui Yang, Hao Luan, Zhuyang Yu, Jin Wei, Ping Chen, Xiaoyan Sun†, Jun Dai 原文链接：https://arxiv.org/html/2609.14723v1 摘要 现代大语言模型（LLM）智能体越来越多地通过聚合外部数据分段来构造提示词（prompt），这些分段包括检...","severity":null,"techs":[],"cves":[],"tags":[],"source":{"id":"seebug-paper","name":"Seebug Paper (Knownsec 404)"},"published_at":"2026-09-24T09:52:50.000Z","fetched_at":"2026-10-27T09:57:34.907Z"}