Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter6

Attack technique

Gradient and representation optimization3Automated search3Conversation structure manipulation3Reasoning-chain manipulation10Cross-modal payloads4Defense-targeted3

System type

Models and APIs2coding agent0Embodied systems and robotics1

System component

Guardrails and judges3Reasoning chains1Vision22Audio3Video2Multimodal27
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationSystem type：Models and APIsSystem type：coding agentSystem type：Embodied systems and roboticsSystem component：Reasoning chainsSystem component：VideoClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2606.09499

    研究者提出针对世界模型的机器人学习管线投毒攻击

    提出 VPH 与 VTH，只改视频帧劫持世界模型并投毒下游策略

    arXiv
    2606.09499
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    Cosmos-Predict 2.5, Cosmos-Predict 2.5 AC, Dino WM and others4
    Abstract只改视频帧经世界模型投毒。

    只改看似安全的视频帧，经世界模型之后才改变下游机器人策略。 问题在于世界模型进入数据生成后，数据集检查看到的仍是安全演示，合成轨迹却可以变危险。

    Paper analysisRead analysis
You have reached the end