Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter3

Attack technique

Gradient and representation optimization3Automated search5Multi-turn escalation2

Impact

Harmful content2Unauthorized actions3

Layer

Prompt layer20Application layer2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
Attack technique：Multi-turn escalationImpact：Harmful contentLayer：Application layerClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2607.03968

    The study reveals workflow-level jailbreaks in IDE programming agents: GitHub Copilot generated harmful content across four backends at 816/816

    提出工作流级越狱，让编程 Agent 在开发任务中写入有害示例

    arXiv
    2607.03968
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.6, Claude Haiku 4.5, Gemini 3.1 Pro and others4
    Abstract作者报告 Copilot 后端会在编码工作流中生成其在单轮条件下通常拒绝的有害答案。

    这是一项生产 IDE 编码智能体的工作流越狱研究，受测对象是 Copilot 的四个模型后端，而非评测流水线中的名义目标。

    Paper analysisRead analysis
  2. 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