Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Attack type

Jailbreaks7Prompt injection41Poisoning and backdoors29Extraction and theft2Malicious use6

System type

Models and APIs61LLM applications11AI Agent9coding agent2Browser and computer use0Multi-agent systems3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftSystem type：coding agentSystem type：Browser and computer useClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.09865

    CGMIA：用成员推理攻击检测代码生成基准的数据泄漏

    提出 CGMIA，检测代码生成基准样本是否泄漏进训练集

    arXiv
    2609.09865
    Published
    Layer
    Model layer
    Setting
    coding agent
    Attacker
    Gray-box
    Evaluated models
    Qwen2.5-Coder (3B), CodeGemma (2B), DeepSeek-Coder (1.3B) and others5
    AbstractCGMIA 融合相似度、通过率、困惑度与 CodeBERT，在模拟泄漏上优于八个 MIA 基线。

    CGMIA 用成员推断检测代码生成基准是否泄入 LLM 训练集，使评测不依赖对训练语料的直接访问。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.01677

    Skill-as-API：面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词

    arXiv
    2609.01677
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。

    Paper analysisRead analysis
You have reached the end