Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter3

Attack type

Prompt injection4

Impact

Unauthorized actions4

System type

Models and APIs284LLM applications47AI Agent153coding agent25science agent4web agent8Browser and computer use4Multi-agent systems14Embodied systems and robotics5

Attack surface / entry point

User input4Web pages and interfaces22Documents and messages4Tool responses3Images, audio and video4

Layer

Application layer8
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
System type：web agentAttack surface / entry point：User inputAttack surface / entry point：Documents and messagesClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2610.05586

    AgentDoxx：联网搜索 Agent 对匿名访谈文本的再识别评测

    构建 AGENTDOXX 基准，评测联网搜索 Agent 对匿名访谈的再识别

    arXiv
    2610.05586
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5.6 Terra, GPT-5 Mini, GPT-4.1 Mini and others10

    Abstract论文提出了已知身份的重识别基准 AGENTDOXX，揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。

    Paper analysisRead analysis
  3. AttacksarXiv 2605.08310

    WebTrap：针对浏览器 Agent 导航过程的中途劫持注入攻击

    提出 WebTrap 三阶段陷阱，中途劫持浏览器 Agent 完成攻击后再返回用户任务

    arXiv
    2605.08310
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    DeepSeek-V3.1-Terminus, Gemini-2.5-Flash, GLM-4.5-Air and others5
    AbstractWebTrap 把攻击目标嵌进用户流程中途执行再返回。

    WebTrap 是针对长程网页与文件导航的中途劫持注入，目标是在完成攻击动作后仍回到用户任务。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2512.23128

    牛津等发布 TRAP 基准

    构建 TRAP 基准，评测网页 Agent 被界面提示注入劫持任务的情况

    arXiv
    2512.23128
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5, Claude Sonnet 3.7, Gemini 2.5 Flash and others6
    Abstract论文提出了基于五维模块化攻击空间的 TRAP 基准，评估了六个模型在真实网页环境中的注入风险。

    研究定位：针对网页自主智能体易受外部界面提示注入攻击的问题，构建了基于真实网站克隆的模块化评测基准 TRAP。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2510.01354

    WAInjectBench 系统评测网页 Agent 的提示注入检测方法

    提出 WAInjectBench 评测网页 Agent 的提示注入检测

    arXiv
    2510.01354
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
    AbstractWAInjectBench 比较网页智能体的提示注入检测：显式线索可被部分检出，隐蔽攻击大多漏检。

    WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击：攻击者改网页，使智能体执行目标动作，而不是用户任务。作者称这是首个此类综合基准。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2503.04957

    SafeArena：首个评估自主网页 Agent 滥用风险的基准

    提出 SafeArena 基准，评测网页 Agent 是否执行故意有害任务

    arXiv
    2503.04957
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, Claude-3.5-Sonnet, Qwen-2-VL-72B and others5
    AbstractSafeArena 用配对任务和 ARIA 评测网页智能体的故意滥用。

    SafeArena 评测自主网页智能体是否会执行用户故意给出的恶意网页任务。。

    Paper analysisRead analysis
You have reached the end