Skip to content

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

Oct 13 · Tuesday

All papers

Found 11 papers
Filter6

Attack type

Prompt injection10Poisoning and backdoors9

Defense type

Detection and filtering3Instruction–data separation5Permissions and approval8Monitoring and auditing1

Impact

Unauthorized actions8

System type

AI Agent11coding agent0Multi-agent systems3

Attack surface / entry point

User input29Web pages and interfaces26Documents and messages20Tool responses46Tool and skill descriptions17Code repositories and dependencies4Retrieval corpus3Memory writes11Inter-agent messages6Distribution channels9

Layer

Application layer11

System component

Memory9Permissions and sandboxing5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 230papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationDefense type：Permissions and approvalDefense type：Monitoring and auditingSystem type：AI AgentSystem type：coding agentAttack surface / entry point：Memory writesClear all

Another 230papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  4. DefensesarXiv 2610.00371

    FlowReview：以授权配对评测控制多智能体组合信息流

    提出 FlowReview，用授权配对与确定性提交门控控制多智能体组合信息流

    arXiv
    2610.00371
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Sonnet 4.5, Haiku 4.5, Qwen3-32B and others5
    Abstract配对标准要求拒绝禁止使用并完成授权使用，FlowReview 把三项审查接到执行。

    这篇工作把多智能体安全写成一件必须同时成立的事：拦住组合信息所启用的禁止使用，并完成同一场景里任务所需的授权使用。

    Paper analysisRead analysis
  5. DefensesarXiv 2609.17648

    多智能体 LLM 流水线中的信任传播与结构隔离

    用任务绑定令牌和策略预言机拦住多智能体流水线的未授权执行

    arXiv
    2609.17648
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gemma4:31b-cloud
    Abstract结构性授权拦住了记忆投毒的未授权执行，持密钥时承重的是策略预言机。

    作者在一条会改写沙箱邮件库的四智能体流水线上，检查低权限失陷会不会变成未授权的真实动作。

    Paper analysisRead analysis
  7. DefensesarXiv 2609.29647

    AgentKernel：面向 Agent 的可信原生操作系统内核

    提出 AgentKernel，用四支柱强制中介 Agent 的输入、工具与记忆

    arXiv
    2609.29647
    Published
    Layer
    Application layer
    Setting
    AI Agent
    AbstractAgentKernel 是四支柱智能体 OS 设计，安全论证未附带实测数字。

    AgentKernel 是把安全做成组织原则的智能体 OS 架构，不是带跑分的攻防评测。

    Paper analysisRead analysis
  10. DefensesarXiv 2606.24322

    Protecting LLM agent long-term memory from poisoning: tamper-evident, source-bound permissions and machine-checkable guarantees

    提出 TMA-NM，以写时来源绑定抵御 Agent 长期记忆投毒

    arXiv
    2606.24322
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gpt-5-chat, gpt-4o-mini, claude-opus-4.1 and others8
    AbstractTMA-NM 用来源绑定的行动权限挡住记忆洗白。

    TMA-NM 把 LLM 智能体长期记忆的行动权限绑到写时来源，用来挡住跨会话记忆投毒。

    Paper analysisRead analysis
  11. 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

    arXiv
    2603.11619
    Published
    Layer
    Application layer
    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