Skip to content

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

Oct 13 · Tuesday

All papers

Found 9 papers
Filter5

Attack type

Prompt injection8Poisoning and backdoors6

Defense type

Detection and filtering5Instruction–data separation7Permissions and approval11Monitoring and auditing2

Impact

Unauthorized actions6

System type

AI Agent9

Attack surface / entry point

User input19Web pages and interfaces24Documents and messages19Tool responses37Tool and skill descriptions16Code repositories and dependencies3Memory writes6Inter-agent messages5Distribution channels8

Layer

Application layer9

System component

Memory6Permissions and sandboxing4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationDefense type：Monitoring and auditingAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Memory writesLayer：Application layerClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2610.02569

    Pincer：用数字分身学习用户偏好并执行动态最小权限

    为 Agent 提出资源层授权系统 Pincer，用数字分身执行动态最小权限

    arXiv
    2610.02569
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude Haiku 4.5, Muse Spark 1.2 Contributor
    AbstractPincer 在资源层以三票合取做授权。

    Pincer 是加在现成 coding agent 上的资源层授权防御：用只受用户侧信息影响的 digital twin 做动态最小权限，并与 tool-call 层防御并存。要处理的是用户维护策略带来的权限蠕变和授权疲劳，以及不学习用户策略的 tool-call 分类器。作者引述工作称 auto mode 会放行多数不安全操作，并认为推理代码或复杂 shell 的效果在这一层不实际。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.35659

    Tracekit：面向自主编码 Agent 的防篡改意图-推理-动作审计系统

    提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改

    arXiv
    2609.35659
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (claude -p, version 2.1), 独立评审（同一 CLI，无工具）
    AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。

    Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。

    Paper analysisRead analysis
  4. 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
  8. 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
  9. 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