Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter5

Attack technique

Gradient and representation optimization3Multi-turn escalation0Cross-modal payloads2

System type

Models and APIs64AI Agent2coding agent0

Layer

Prompt layer2Application layer17
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Attack technique：Multi-turn escalationAttack technique：Cross-modal payloadsSystem type：AI AgentSystem type：coding agentLayer：Prompt layerClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2608.10393

    DURA：用扩散模型生成自然对抗补丁攻击 VLA 机器人模型

    提出 DURA，用扩散模型生成自然对抗补丁操控 VLA 机器人动作

    arXiv
    2608.10393
    Published
    Layer
    Prompt layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA-7B, π0-FAST, openvla-7B
    AbstractDURA 用扩散潜空间轨迹生成自然补丁，白盒与黑盒都能把 VLA 导向指定动作。

    DURA 是针对 VLA 的扩散式、补丁内容不受限的机器人攻击，同时支持白盒梯度和只看动作输出的黑盒。

    Paper analysisRead analysis
You have reached the end