大模型对齐与安全

Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts

Sentra-Guard：一种实时多语言对抗对抗性LLM提示的防御系统

Md. Mehedi Hasan, Sk Tanzir Mehedi, Ziaur Rahman, Rafid Mostafiz, Md. Abir Hossain

专题命中 提示注入 ：jailbreak(abstract)；prompt injection(abstract)；分类 cs.AI

AI总结 Sentra-Guard通过混合架构和分类器-检索器融合模块，实时检测并缓解针对大语言模型的劫持和提示注入攻击，实现多语言鲁棒性与高检测率。

Comments 11 pages, 5 figures. Preprint version under review in the area of Artificial Intelligence (cs.AI)

Parasites in the Toolchain: A Large-Scale Analysis of Attacks on the MCP Ecosystem

工具链中的寄生体：对MCP生态系统的大型分析

Shuli Zhao, Qinsheng Hou, Zihan Zhan, Yanhao Wang, Yuchong Xie, Yu Guo, Libo Chen, Shenghong Li, Zhi Xue

专题命中 提示注入 ：prompt injection(abstract)

AI总结 研究发现MCP生态中存在寄生工具链攻击，攻击者通过恶意指令渗透工具链，窃取隐私数据，揭示MCP缺乏安全隔离机制，需加强防御。

Comments Accepted by IEEE Symposium on Security and Privacy, 2026