Skip to content

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

Oct 12 · Monday

Backdoors and poisoning · Papers

Found 1 paper
Filter2

Attack technique

Gradient and representation optimization1Defense-targeted3Dormant triggers18

Layer

Training and data layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack technique：Gradient and representation optimizationLayer：Training and data layerTopic: Backdoors and poisoningClear all
  1. 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