Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter4

Attack technique

Gradient and representation optimization7Automated search23Encoding and obfuscation13Role-play and persuasion8Conversation structure manipulation3Cross-modal payloads5Defense-targeted8Dormant triggers11Selection manipulation4

System type

Models and APIs43LLM applications4AI Agent11coding agent1web agent4Browser and computer use0Embodied systems and robotics3

Attack surface / entry point

Images, audio and video4

Layer

Application layer5

System component

Vision4Multimodal5
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.
Attack technique：Cross-modal payloadsSystem type：LLM applicationsSystem type：coding agentSystem type：Browser and computer useClear all

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

  2. Evaluation and benchmarksarXiv 2609.35912

    MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

    提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作

    arXiv
    2609.35912
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6

    Abstract论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。

    Paper analysisRead analysis
  3. 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