Skip to content

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

Oct 12 · Monday

Jailbreaks and attacks · Papers

Found 4 papers
Filter1

Attack type

Jailbreaks4

Impact

Harmful content4

System type

AI Agent3

Attacker access

Black-box3White-box3

Attack surface / entry point

User input112Tool responses4Tool and skill descriptions3Images, audio and video35Weights and gradients6

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack surface / entry point：Tool responsesTopic: Jailbreaks and attacksClear all
  3. AttacksarXiv 2601.05466

    Jailbreaking large language models through reinforcement learning with iterative tool disguise attacks

    提出 iMIST，用工具伪装和 PPO 迭代越狱大语言模型

    arXiv
    2601.05466
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    DeepSeek-V3, Qwen3-32B, GPT-OSS-120B
    AbstractiMIST 用工具伪装和在线 PPO 做黑盒越狱，Table I 中 JADES 高于同格基线。

    iMIST是黑盒越狱方法：把恶意查询伪装成合法工具调用，再用在线强化学习把响应的有害性分数往上推。

    Paper analysisRead analysis
You have reached the end