Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter4

Attack type

Prompt injection7

Defense type

Model hardening3Detection and filtering10Instruction–data separation12Permissions and approval10Monitoring and auditing7Watermarking and provenance1

Impact

Unauthorized actions6

System type

AI Agent8

Attack surface / entry point

User input12Web pages and interfaces7Documents and messages8Tool responses16Tool and skill descriptions5Distribution channels4

Layer

Model layer7Application layer8

System component

Monitors5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Defense type：Monitoring and auditingDefense type：Watermarking and provenanceAttack surface / entry point：Documents and messagesLayer：Application layerClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2610.09793

    用时序逻辑监控工具 Agent

    提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链

    arXiv
    2610.09793
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Abstract形式化验证可有效识别多步攻击，但其有效性高度依赖轨迹的可信历史记录。

    这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。

    Paper analysisRead analysis
  3. DefensesarXiv 2610.05163

    Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark

    提出 PAA 方法，在边界动作前审计长流程智能体的分阶段提示注入

    arXiv
    2610.05163
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (v2.1.172, Claude Sonnet 5), Codex CLI (v0.144.0, GPT-5.5)
    Abstract论文针对长流程注入提出边界动作审计与 PAA，在保持低误阻的同时实现高拦截率。

    本研究针对长流程智能体在执行任务时面临的分阶段间接提示注入威胁，提出了在动作生效前进行拦截的边界动作审计框架与路径对齐归因方法。

    Paper analysisRead analysis
  4. DefensesarXiv 2610.00327

    Actions with Receipts：为工具智能体审计绑定声明、证据与执行

    提出 EC-Agent 联合回执，绑定工具智能体的主张、证据与执行并支持重放审计

    arXiv
    2610.00327
    Published
    Layer
    Application layer
    Setting
    AI Agent
    AbstractEC-Agent 把主张、片段、执行前缀和来源状态绑成可重放回执，并把完整性与语义支持分开判定。

    EC-Agent 为工具智能体的审计增加一份可重放的联合回执：它同时绑定发出的主张、精确来源片段、有序执行前缀，以及该次执行看到的来源版本和访问状态。

    Paper analysisRead analysis
  7. 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

    arXiv
    2605.17380
    Published
    Layer
    Application layer
    Setting
    coding agent

    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
  8. DefensesarXiv 2602.20708

    ICON：基于推理时纠正的 Agent 间接提示注入防御

    Proposes inference-time defense ICON, which detects attention over-focusing and redirects to correct indirect prompt injection in agents.

    arXiv
    2602.20708
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen-3-8B, Llama-3.1-8B, Mistral-8B and others6
    AbstractICON detects over-focusing and redirects at inference time to balance IPI safety and task utility.

    ICON detects attention over-focusing from IPI at inference time and redirects, avoiding refusal that would terminate the agent trajectory.

    Paper analysisRead analysis
You have reached the end