Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack technique

Cross-modal payloads2Defense-targeted1

Attacker access

Black-box37Gray-box6White-box9No-box (offline transfer)3
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 technique：Cross-modal payloadsAttack technique：Defense-targetedAttacker access：No-box (offline transfer)Clear all

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

  2. AttacksarXiv 2603.01414

    通过动作级操纵越狱具身 LLM

    提出 Blindfold，用动作级操纵越狱具身 LLM

    arXiv
    2603.01414
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    Attacker
    No-box (offline transfer)
    Evaluated models
    Llama-3.1-8B, DeepSeek-R1-14B, Gemma-3-27B and others8
    AbstractBlindfold 以动作级代理规划越狱具身 LLM，作者称可绕过语义检查并在仿真与真机生效。

    Blindfold 是面向具身 LLM 规划模块的 no-box 攻击，把恶意意图改写成看似良性的动作序列。

    Paper analysisRead analysis
  3. AttacksarXiv 2602.09431

    Grounding-driven attack: Improving the transferability of encoder-based adversarial attacks to large vision-language models

    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
You have reached the end