Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack type

Prompt injection3

Impact

Unauthorized actions7Output manipulation3

System type

LLM applications6AI Agent10coding agent0Browser and computer use2Multi-agent systems1

Attack surface / entry point

User input7Web pages and interfaces3Documents and messages4Code repositories and dependencies4Inter-agent messages10Distribution channels4

Layer

Application layer3
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 manipulationSystem type：coding agentSystem type：Browser and computer useSystem type：Multi-agent systemsAttack surface / entry point：Web pages and interfacesClear all

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

  2. Evaluation and benchmarksarXiv 2610.06898

    DIBench：面向移动 GUI 智能体多候选选择决策完整性的安全基准

    用 DIBench 评测移动 GUI 智能体被 UI 注入后的决策完整性

    arXiv
    2610.06898
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    Qwen2.5-VL(32B), Qwen3-VL(32B), GUI-Owl(32B) and others7

    Abstract论文提出移动智能体决策完整性基准 DIBench，发现欺诈 UI 注入诱导目标选择并推高完成率，通用防御收益不稳定。

    Paper analysisRead analysis
  3. AttacksarXiv 2608.00718

    研究揭示多智能体 LLM 流水线的结构性漏洞

    提出多智能体流水线的边界攻击，使对抗内容作为可信输入跨层传播

    arXiv
    2608.00718
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5-mini, Claude Sonnet 4.5, Kimi K2.5
    Abstract缺边界校验使对抗内容跨智能体传播，作者称这是架构属性而非模型能力。

    作者把多智能体 LLM 流水线的对抗问题定义为缺少边界校验，并用生产轨迹和受控实验检查脆弱性来自架构还是骨干模型。中间输出未经验证就传给下游。作者认为，一旦某级接受对抗内容，后续智能体会把它当作可信输入。

    Paper analysisRead analysis
You have reached the end