Skip to content

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

Oct 12 · Monday

All papers

Found 9 papers
Filter4

Attack type

Prompt injection5

Impact

Unauthorized actions16Data and privacy leaks6Output manipulation5Availability and reliability4

System type

LLM applications63AI Agent131coding agent16science agent7web agent9Multi-agent systems28Embodied systems and robotics3

Attack surface / entry point

Web pages and interfaces4

Layer

Application layer9
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Impact：Output manipulationImpact：Availability and reliabilitySystem type：web agentLayer：Application layerClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  4. Evaluation and benchmarksarXiv 2609.19140

    AgentLSD：在对抗性任务污染下评测 AI 安全 Agent

    评测安全 Agent 在对抗性任务污染下的解题成功与开销

    arXiv
    2609.19140
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    Gemma-4 31B, DeepSeek-V4 Flash, GPT-OSS 120B and others6
    AbstractAgentLSD 用配对 web CTF 表明，欺骗性环境证据会改变安全智能体的解题率与工作量。

    AgentLSD 是一个对照框架，用来测量安全智能体在任务本身不变时，对对抗性任务污染的反应。

    Paper analysisRead analysis
  5. AttacksarXiv 2608.04565

    Researchers propose Breadcrumbing long-range attack that can hijack the evidence chain of DeepResearch-style search agents

    提出权威链劫持与轨迹引导策略演化，劫持搜索 Agent 的证据链

    arXiv
    2608.04565
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    Qwen3.5-9B, Gemma4-31B, DeepResearch and others7

    Abstract论文揭示了多步搜索智能体在受限中间人操纵下的脆弱性，提出 ACH 策略与 TGSE 演化方法并完成系统验证。

    Paper analysisRead analysis
  7. AttacksarXiv 2603.16960

    针对现代视觉语言模型的对抗攻击

    对开源视觉购物智能体实施商品图对抗攻击并诱导买错

    arXiv
    2603.16960
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    LLaVA-v1.5-7B, Qwen2.5-VL-7B
    Abstract作者称 LLaVA 易被三种攻击诱导买错，Qwen 正确购买率仍接近其干净条件。

    作者在自建电商环境里比较两个开源 VLM 购物智能体对图像对抗扰动的鲁棒性。

    Paper analysisRead analysis
  8. Risky behaviorarXiv 2602.00851

    研究提出说服传播现象：无关说服性对话会改变 AI Agent 的任务执行行为

    测量任务无关说服对 Agent 编码与网页研究行为的影响

    arXiv
    2602.00851
    Published
    Layer
    Application layer
    Setting
    web agent, coding agent
    Evaluated models
    gpt-4.1-nano, mistral-nemo-12b, llama-3.1-8b
    Abstract任务无关说服会在轨迹上留下任务相关的行为痕迹，但立场易感性不能稳定预测其幅度。

    这篇工作测量一件事：与任务无关的说服进入对话之后，AI 智能体执行后面的编码或网页研究时，轨迹是否系统性不同，以及“更容易被说服”能否预测差有多大。

    Paper analysisRead analysis
You have reached the end