Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter5

System type

Models and APIs3

Attack surface / entry point

Memory writes0Weights and gradients3

Layer

Model layer3Application layer0Training and data layer3

System component

MCP and skills7Memory40RAG4Guardrails and judges5Reasoning chains3Permissions and sandboxing7Fine-tuning and open weights30Image generation3Multimodal6
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 surface / entry point：Memory writesAttack surface / entry point：Weights and gradientsLayer：Application layerLayer：Training and data layerSystem component：Image generationClear all

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

  1. AttacksarXiv 2610.05453

    研究者提出 Privacy-Leaking Watermarks，可在本地多模态模型中泄露对话隐私

    提出 PLW，用微调把先前对话敏感触发编码进后续生成图像

    arXiv
    2610.05453
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    OmniGen2, BAGEL-7B

    AbstractPLW 把先前对话线索写成后续图像中的隐水印，检出随触发、模型和间隔变化。

    Paper analysisRead analysis
You have reached the end