Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter2

Impact

Harmful content7Unauthorized actions69Data and privacy leaks9Output manipulation17Availability and reliability2Oversight failure3

Attack surface / entry point

User input9Web pages and interfaces3Tool responses2Tool and skill descriptions3Images, audio and video5Training data7Weights and gradients3Distribution channels4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilityAttack surface / entry point：Tool responsesClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.03448

    Study retests 15 prompt injection detectors: benchmark scores poorly predict agent deployment performance

    重测提示注入检测器在 Agent 工具输出上的检出与任务阻断

    arXiv
    2610.03448
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Horizon-Labs, Wolf Defender, Prismor-1.5B and others15

    Abstract论文揭示公开基准无法反映智能体检测器表现，检测能力源于输入格式相似而非通用防御，建议基于工具输出与低误报评测。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.28585

    论文提出持久计费状态概念，揭示工具调用 LLM Agent 的拒绝钱包攻击与防御

    定义工具调用 Agent 的持久计费状态，提出拒绝钱包攻击与防御

    arXiv
    2609.28585
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4o, GPT-4o-mini, Mistral-Large and others7
    Abstract已准入工具返回的跨轮保留会重复计费。

    这篇工作把工具调用智能体里跨轮保留、并被提供商反复计费的外部工具返回定义为 persistent billable state，并把它的主机侧再次送入决定当作控制点。。

    Paper analysisRead analysis
You have reached the end