Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter2

System type

Models and APIs3

Attacker access

Black-box94Gray-box5White-box16No-box (offline transfer)3

Layer

Prompt layer3

System component

Multimodal3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.
Attacker access：No-box (offline transfer)Layer：Prompt layerClear all

Another 305papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2602.09431

    Grounding 驱动的攻击：提升基于编码器的对抗攻击对大型视觉语言模型的迁移性

    提出 GDA，将图像对抗扰动对齐文本接地证据并迁移攻击视觉语言模型

    arXiv
    2602.09431
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    No-box (offline transfer)
    Evaluated models
    LLaVA, Qwen2.5-VL, InternVL3 and others10
    AbstractGDA 把扰动对准文本接地证据，作者称这提高了异构 LVLM 上的零查询黑盒迁移性。

    GDA 是面向异构 LVLM 的零查询黑盒编码器迁移攻击。。

    Paper analysisRead analysis
  3. AttacksarXiv 2503.01839

    研究者用微调大语言模型越狱带安全护栏的文生图模型

    提出 PromptTune，微调 LLM 改写提示以越狱文生图护栏

    arXiv
    2503.01839
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    No-box (offline transfer)
    Evaluated models
    SDXL-Turbo, MACE, SafeGen
    AbstractLLM 改写可提高过滤器绕过率。

    PromptTune 用微调 LLM 改写提示词，攻击带安全过滤器或对齐的文生图模型。

    Paper analysisRead analysis
You have reached the end