Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter6

Attack type

Jailbreaks6Prompt injection91Poisoning and backdoors22Extraction and theft4Detection evasion5Malicious use3

Attack surface / entry point

User input11Web pages and interfaces1Inter-agent messages1Images, audio and video1Training data0

Layer

Prompt layer4Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Attack type：Malicious useAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Inter-agent messagesAttack surface / entry point：Images, audio and videoAttack surface / entry point：Training dataLayer：Application layerClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2609.33102

    ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架

    提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果

    arXiv
    2609.33102
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5

    AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。

    Paper analysisRead analysis
  3. DefensesarXiv 2603.01544

    RA-Det：利用鲁棒性不对称检测 AI 生成图像

    提出 RA-Det，利用鲁棒性不对称检测 AI 生成图像

    arXiv
    2603.01544
    Published
    Layer
    Application layer
    Setting
    LLM applications
    AbstractRA-Det 把扰动下特征漂移差变成检测信号，平均 ACC 高于表中通用检测器，但不是每行最高。

    RA-Det 是合成图像检测器，用扰动下的表示稳定性差异代替外观痕迹。

    Paper analysisRead analysis
You have reached the end