Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter4

Attack technique

Gradient and representation optimization1

Attack surface / entry point

User input4Web pages and interfaces4Documents and messages1Images, audio and video25Weights and gradients0

System component

Vision1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack surface / entry point：Documents and messagesAttack surface / entry point：Weights and gradientsSystem component：VisionClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2606.12716

    PaperGuard：针对多模态 AI 同行评审的攻击与防御基准

    提出 PaperGuard，用图文注入与梯度扰动抬高自动审稿分数并检测恶意指令

    arXiv
    2606.12716
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Claude-sonnet-4.5, GPT-4o, GPT-4.1 and others11
    AbstractPaperGuard 测到提示注入与白盒视觉抬分，并比较分块检索防御。

    PaperGuard同时评测并检测多模态 AI 审稿中的评分操纵。

    Paper analysisRead analysis
You have reached the end