Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
Proposes RATED, which reranks agent tool retrieval using execution feedback
Published Oct 10
Evaluated models DRAGON 提出 HTN 协调层,在执行前固定多服务器 MCP 工具顺序
Published Sep 28 Abstract 作者提供可重放的 MCP 协调架构,但未用实测基线量化相对 LLM 的成本改善。HTN 规划在这里承担跨服务器工具协调层的角色。 作者关注 MCP 宿主逐步选择工具时的复现、推理成本和执行前检查问题。
测量远程 MCP 生态的网络集中度与认证对扫描的阻挡
Published Sep 17 提出成本感知的 MCP 编排框架,用确定性利用图与免费层模型做自动化渗透测试
Published Sep 16 Abstract 确定性利用图加免费层级联在十次自建运行上测得付费成本为零。PentestChain 是一个十阶段、经 MCP 暴露的自动渗透框架,用确定性利用图把 7B 本地模型挡在利用关键路径之外,并把每次交战的美元成本当作实测指标。 。
综述自主渗透智能体的继承攻击、架构攻击及护栏缺口
Published Sep 15 Abstract 用双轴分类连接渗透智能体的架构、攻击与护栏,并认为现有防御仍按组件分开。这是一篇关于自主 AI 渗透测试智能体的安全综述:用架构和生命周期两轴整理威胁与护栏,不做新的攻击实验。
用 SAVER 框架综述自演化智能体的状态复用安全
Published Sep 8 Abstract SAVER 用状态转移追踪自演化安全:合法状态可经复用变不安全,后代修复证据仍少。SAVER 是一篇关于自演化智能体安全的转移中心综述:安全对象从单次回答或单次授权动作,转到可复用状态在多次转移中的谱系。
系统梳理 LLM-as-a-Judge 安全研究并提出角色分类法
Published Mar 31 Abstract 这是一篇 LaaJ 安全 SoK:按五类角色整理文献,并汇总被引量化结果。
系统化 LLM Agent 技能的定义、生命周期与治理
Published Feb 24 Abstract 技能 SoK 用四元组、生命周期和七种模式归档文献,并转述策划与自生成技能的效用差。这是一篇 LLM 智能体技能层的知识系统化,不是作者新做的攻击或防御实验。 。
You have reached the end