Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Attack technique

Gradient and representation optimization1Conversation structure manipulation0Defense-targeted0

System type

Models and APIs18AI Agent1

Layer

Prompt layer4Model layer1Application layer30
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack technique：Conversation structure manipulationAttack technique：Defense-targetedSystem type：AI AgentLayer：Model layerClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.06083

    研究者提出面向深度强化学习的轨迹级可迁移黑盒对抗攻击

    提出轨迹级可迁移对抗攻击，降低深度强化学习策略的期望回报

    arXiv
    2610.06083
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    DQN, Double DQN (DDQN)
    Abstract轨迹级后退视界攻击在 CartPole 上比逐步 FGSM 类和 Sign 噪声更压低回报。

    这项工作研究 DRL 上的迁移式黑盒观测攻击：受害参数不可访问时，在白盒代理上造扰动再迁移。

    Paper analysisRead analysis
You have reached the end