Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 13 papers

Another 233papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.10612

    PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器

    提出 PyCache Trap,用字节码缓存替换绕过 Agent 技能扫描器

    Published
    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。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.02861

    论文提出在 Kubernetes 上保护 AI Agent 的七层纵深防御框架与参考架构

    提出 Kubernetes 运维智能体的七层纵深防御框架与参考架构

    Published
    Setting
    AI Agent
    Abstract把运维智能体当不可信租户,用七层控制在完全攻破假设下约束行动。

    把 Kubernetes 上的运维智能体当作不可信租户,在假定提示注入已完全控制其工具选择的前提下,用基础设施重建数据面与控制面的边界。要解决的是:智能体读日志、注解、工单或 MCP 工具描述时,这些内容可以变成它带着自身凭据执行的命令。模型对齐和分类器只降低概率。

    Paper analysisRead analysis
  3. AttacksarXiv 2609.39607

    Pretext 攻击绕过 NVIDIA SkillSpector 等 Agent 技能扫描器

    提出 PRETEXT 攻击,迭代改写技能文本绕过技能扫描器并让 Agent 执行木马

    Published
    Setting
    AI Agent
    Attacker
    White-box
    Evaluated models
    glm (z-ai/glm-5.1), qwen3t (qwen/qwen3-235b-a22b-thinking-2507), gpt-oss (openai/gpt-oss-120b)
    Abstract论文提出了针对多阶段技能检测器的白盒攻击,揭示了单纯依赖大模型自适应检测的局限。

    PRETEXT 是一项针对基于“静态规则加语义大模型”的智能体技能安全检测框架的白盒攻击与协同进化评估研究。

    Paper analysisRead analysis
  4. AttacksarXiv 2609.30383

    研究者提出技能级联攻击

    提出技能级联攻击,把有害目标拆散到多个技能里绕过单技能扫描

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.4 Mini, Claude Opus 4.6 and others11

    Abstract论文探讨了多技能智能体系统面临的技能级联攻击风险,提出自动化红队框架与基准集,指出跨技能交互存在安全防护盲区。

    Paper analysisRead analysis
  5. 研究提出 ACE 语料库,评估内核级证据对 Agent 安全检测的有效性

    构建 ACE 语料,评测内核级证据对 Agent 攻击检测的有效性

    Published
    Evaluated models
    AdaBoost, XGBoost, TabPFN and others10
    AbstractACE 用配对的内核与应用层证据表明,syscall 痕迹可判别智能体攻击,两层组合通常更好。

    ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。

    Paper analysisRead analysis
  6. DefensesarXiv 2608.21101

    ClawSentry:面向自主 LLM Agent 的渐进式多层安全监控网关

    提出 ClawSentry 多层监控网关,在技能准入和运行时拦截恶意技能与隐藏指令

    Published
    Evaluated models
    Codex/GPT-5.4, Codex/GPT-5.5, Claude Code/GLM-5.1 and others6
    AbstractClawSentry 用包准入、三级运行时门控和反绕过,压低 skill 攻击并保住干净任务。

    ClawSentry 是挂在智能体运行时之外的安全监督网关,用来同时盖住 skill 执行的多个生命周期边界,并把已被拒绝的效果记到会话里。

    Paper analysisRead analysis
  7. DefensesarXiv 2608.05578

    AMS 工具通过激活分析检测语言模型的安全训练改动

    提出 AMS,用激活分离与方向相似度检测安全训练改动

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.2-3B-Instruct, Llama-3.2-1B-Instruct and others14
    AbstractAMS 按激活签名把安全改动分四类,前三类可由两级扫描覆盖,行为微调会漏。

    AMS 是面向开放权重模型、部署前使用的激活扫描器,用来看安全训练被拿掉或改写之后,激活空间里还留着什么几何痕迹。

    Paper analysisRead analysis
  8. SkillVetBench:用 LLM-as-Judge 评估开源 LLM Agent 技能的多维安全风险

    提出 SkillVetBench 评估开源 Agent 技能的多维安全风险

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen2.5-14B-Instruct, Qwen2.5-32B, Llama-3.1-70B and others6

    Abstract公开排行榜用 LLM-as-Judge 给技能分列 SARS 与 CVSS,并对照市场官方审查。

    Paper analysisRead analysis
  9. DefensesarXiv 2605.17380

    Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months

    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

    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。

    Paper analysisRead analysis
  10. AttacksarXiv 2604.03890

    From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

    Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
  11. DefensesarXiv 2603.12644

    Revealing security threats and defense architectures for autonomous agents: an OpenClaw case study

    Reviews threats to autonomous agents and proposes a full-lifecycle defense blueprint, FASA

    Published
    Setting
    AI Agent
    AbstractUsing OpenClaw as an example, it divides risks into three layers and uses FASA to describe defense from input to system execution.

    This is a threat review and defense architecture report using OpenClaw as a case study, not a scored attack or defense evaluation.

    Paper analysisRead analysis
  12. DefensesarXiv 2603.11619

    Taming OpenClaw: Security Analysis and Mitigation of Threats in Autonomous LLM Agents

    Proposes a defense-in-depth aligned with the five stages to mitigate cross-stage threats to autonomous agents

    Published
    Setting
    AI Agent
    AbstractThis is a lifecycle threat analysis and layered mitigation design for OpenClaw, with the cases serving as qualitative evidence.

    This is a lifecycle threat analysis of OpenClaw, accompanied by a set of layered mitigation designs. The problem addressed is: when autonomous agents connect instant messaging, persistent memory, third-party plugins, and high-privilege execution, attacks are no longer limited to single-turn jailbreaks but can compound across multiple stages from initialization to execution. The authors argue that defenses hardening only individual interfaces cannot stop such cross-temporal attacks.

    Paper analysisRead analysis
You have reached the end