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 injection4

Model risks

Dangerous agent actions3

Defense type

Detection and filtering4Monitoring and auditing4

Impact

Unauthorized actions5

System type

Models and APIs110LLM applications53AI Agent110coding agent29science agent6web agent4Browser and computer use5Multi-agent systems11Embodied systems and robotics5

Attack surface / entry point

Web pages and interfaces3

Layer

Application layer9

System component

MCP and skills3RAG3Guardrails and judges5Monitors4Permissions and sandboxing5Vision12Embeddings0Multimodal12
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.
System type：web agentSystem type：Browser and computer useSystem component：Guardrails and judgesSystem component：MonitorsSystem component：EmbeddingsClear all

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

  3. DefensesarXiv 2609.22724

    MATE：面向移动 Agent 的策略感知安全审计方法

    提出移动 Agent 轨迹审计器 MATE，判断轨迹是否违反可编辑安全策略

    arXiv
    2609.22724
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Attacker
    Black-box
    Evaluated models
    MATE-0.5B, MATE-1.5B, MATE-3B
    AbstractMATE 用合成轨迹微调轻量审计器，在可编辑策略下判断移动智能体轨迹是否违规并给出解释。

    MATE 是面向移动 GUI 智能体的轻量策略条件轨迹审计器，在给定自然语言安全策略时判断轨迹是否违规并解释原因。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2604.06240

    研究者开源 Universal Verifier 与 CUAVerifierBench，用于验证计算机使用 Agent 轨迹

    构建 Universal Verifier 核验计算机使用 Agent 轨迹

    arXiv
    2604.06240
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5.2, GPT-4o, o4-mini and others8
    Abstract四条设计原则叠成 Universal Verifier，作者称其与人类一致程度相当且假阳性近零。

    Universal Verifier 给计算机使用轨迹打过程分和结果分，并定位失败。CUAVerifierBench 用人工标签衡量这种验证器。

    Paper analysisRead analysis
  6. DefensesarXiv 2603.14707

    Visual Confusion Agents: Exploiting and Defending Against Perception Failures in Computer-Use Agents

    Proposes out-of-process dual-channel comparison classification to intercept erroneous clicks by computer-use agents

    arXiv
    2603.14707
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    multi-modal-embed-small
    AbstractPerception errors can be exploited by swapping screen pixels.

    The authors frame CUA's perception failure as a security vulnerability, visual confused deputy: the agent authorizes click(x,y) based on a misread screen, and the actual landing point differs from the element it believes it is clicking.

    Paper analysisRead analysis
  9. 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
You have reached the end