Papers · organized/paper_cards

论文

2 张论文卡片 · 安全与风险

开放获取 全部 绿色 · 724
SSGM框架(Stability and Safety-Governed Memory)
3. SSGM框架(Stability and Safety-Governed Memory)
arXiv:2603.11768 安全与风险 观点 OA · 绿色 被引 13 · S2

通过形式化分析与架构分解,展示 SSGM 如何缓解拓扑引发的知识泄漏(敏感上下文被固化到长期存储),以及有助于防止语义漂移(知识在迭代摘要中退化)。Through formal analysis and architectural decomposition, it is shown how SSGM can mitigate topology-induced knowledge leakage where sensitive contexts are solidified into long-term storage, and help prevent semantic drift where knowledge degrades through iterative summarization.

arXiv-3:A First Look at the Security Issues in the Model Context Protocol Ecosystem
arXiv-3:初探Model Context Protocol生态中的安全问题
arXiv:2510.16558 安全与风险 方法 被引 6 · S2

本文分析了六个公共注册表中共计67,057个服务器,识别出可导致服务器劫持与调用操控的普遍隐患,并实现了MCPInspect——一款集成前分析工具,可检测误导性的工具元数据与可利用的代码漏洞。This paper analyzes 67,057 servers across six public registries and identifies widespread conditions enabling server hijacking and invocation manipulation, and implements MCPInspect, a pre-integration analysis tool that detects misleading tool metadata and exploitable code vulnerabilities.