Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter4

Attack type

Jailbreaks7Prompt injection60Poisoning and backdoors13Extraction and theft4Detection evasion3Malicious use2

Layer

Prompt layer4Model layer5Application layer2

System component

Monitors6Permissions and sandboxing1Multimodal1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：Malicious useLayer：Application layerSystem component：Permissions and sandboxingSystem component：MultimodalClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. Risky behaviorarXiv 2609.30266

    研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹

    测试编程智能体被诱导或自主篡改自身执行轨迹的行为

    arXiv
    2609.30266
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
    Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。

    这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。

    Paper analysisRead analysis
  2. 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