Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Attack type

Jailbreaks16Prompt injection1

Attack technique

Gradient and representation optimization9Automated search1Cross-modal payloads12

System component

MCP and skills8Memory5Multimodal1
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.
Attack type：Prompt injectionAttack technique：Automated searchSystem component：MultimodalClear all

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

  1. AttacksarXiv 2609.04533

    Repeat-After-Me：针对黑盒 VLM 的自适应视觉提示注入攻击

    提出 Repeat-After-Me 自适应视觉提示注入，诱导 VLM 智能体执行指定任务

    arXiv
    2609.04533
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude-Opus-4.7, GPT-5.5, Gemini-3.1-Pro and others6

    Abstract论文提出了针对黑盒 VLM 的前缀诱导自适应视觉提示注入，在多款模型上诱发了工具调用与隐私泄露。

    Paper analysisRead analysis
You have reached the end