Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 13 papers 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.
提出 PyCache Trap,用字节码缓存替换绕过 Agent 技能扫描器
Published Oct 7
Evaluated models CISCO , HSS , AUDITOR and others8 Abstract 论文剖析智能体技能审查与执行脱节盲区,提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。这篇论文研究了智能体技能(Agent Skills)安全扫描中的“审查–执行脱节”问题,并提出了对应的攻击验证与防御方案。
提出 AgentSpy,在系统调用层观测 Agent 行为并检测技能注入
Published Oct 5
Evaluated models gpt-5.6-terra , deepseek-v4-flash , glm-5.3-flash and others4 Abstract 提出了系统级智能体监控框架 AgentSpy,揭示出通过测试背后的非预期行为与注入风险。本研究提出了面向 AI 智能体的系统级外部监控与行为分析框架 AgentSpy 。
提出 ASA 与 AttestMCP,度量并降低 LLM 对输入序列扰动的敏感
Published Oct 2
Evaluated models Gemma-3-27B-Instruct , Gemma-3-4B-Instruct , Llama-3.2-3B-Instruct and others12 提出证据引导的 SKILLLITE,审计部署前恶意 Agent Skill
Published Sep 29
Evaluated models Gemma4:e4b , Qwen3.5:9B , DeepSeek-R1:8B and others4 Abstract SKILLLITE 把证据抽取外置,让紧凑 LLM 只做意图条件下的风险裁决,三个基准上 F1 高于所列基线。SKILLLITE 是面向紧凑、可本地部署 LLM 的恶意 Agent Skill 预执行审计框架,作者单位为南洋理工大学。
提出 SkillSecurer,检测并修补 Agent 技能中的提示注入漏洞
Published Sep 13
Evaluated models Claude Sonnet 5 , Gemini 3.6 Flash , GPT-5.6 Sol and others10 提出 ColluSkill,用跨技能组合绕过 Agent 技能扫描器
Published Aug 10
Evaluated models GPT-5.5 , DeepSeek-V4-Pro , GLM-5.2 Abstract 论文揭示了单技能孤立扫描的盲区,提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。
提出 SkillSentry,用自适应蜜罐世界在安装前检测 Agent 技能是否越出能力契约
Published Aug 4
Evaluated models DeepSeek-V4-Pro , Qwen , Kimi and others4 Abstract 契约加配对执行审计技能越权。SkillSentry 是安装前的动态技能审计,用来发现超出宣称功能的能力漂移。技能一旦安装,就能使用宿主的文件、shell、凭证和网络,而有害分支可能要等特定资源才出现。作者认为,源码或一次性语义判断既不能确认分支会执行,也不能把技能造成的效果与任务或基座智能体的动作分开。
提出 MTGuard,对照 MCP 调用声明与执行痕迹拦截不安全工具调用
Published Jul 28
Evaluated models DeepSeek-V4-Flash , DeepSeek-V4-Pro , GPT-5.6 Luna 提出 SciTrace,为科学发现智能体加入跨阶段安全推理与工具轨迹核验
Published Jun 6
Evaluated models Llama-3.1-70B-Instruct , Qwen2.5-72B-Instruct , DeepSeek-V3 and others4 Abstract SciTrace 把安全推理织入科学智能体各阶段,在 SciSafetyBench 上提高安全指标并保持输出质量。SciTrace 是加在科学发现智能体流水线上的安全框架,不是再在各阶段出口放一个独立过滤器。
提出企业级检测系统 ADR,识别编程 Agent 的提示注入与恶意 MCP
Published May 17 Abstract 提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统,并在生产环境中验证了有效性。
提出谱系图治理层抑制多智能体协作的错误级联
Published Mar 4 Abstract 单一种子可沿固定协作图固化为错误共识。作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播,并用只改消息、不改拓扑的插件压低最终感染。
提出 Tool Obfuscation 并评测函数调用 Agent 的攻防
Published Jan 14
Evaluated models Qwen3:8B , Llama-3.2:3B , Granite3.2:8B and others5 Defenses arXiv 2505.23559 · May 29, 2025 提出 SafeScientist 四层监控,阻止科研智能体执行高风险或不伦理任务
Published May 29, 2025
Evaluated models GPT-4o , GPT-4.1 , GPT-3.5-turbo and others5 Abstract 四层监控加科研安全基准。SafeScientist 是带四层监控的科研智能体框架,并用 SciSafetyBench 评测科学场景中的任务安全。
You have reached the end