Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter5

Attacker access

Black-box3White-box1

Attack surface / entry point

Tool and skill descriptions1Training data0Weights and gradients0

Layer

Prompt layer3Model layer13Application layer1Training and data layer11
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.
Attacker access：White-boxAttack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Training dataAttack surface / entry point：Weights and gradientsLayer：Application layerClear all

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

  1. AttacksarXiv 2609.39607

    Pretext 攻击绕过 NVIDIA SkillSpector 等 Agent 技能扫描器

    提出 PRETEXT 攻击，迭代改写技能文本绕过技能扫描器并让 Agent 执行木马

    arXiv
    2609.39607
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    White-box
    Evaluated models
    glm (z-ai/glm-5.1), qwen3t (qwen/qwen3-235b-a22b-thinking-2507), gpt-oss (openai/gpt-oss-120b)
    Abstract论文提出了针对多阶段技能检测器的白盒攻击，揭示了单纯依赖大模型自适应检测的局限。

    PRETEXT 是一项针对基于“静态规则加语义大模型”的智能体技能安全检测框架的白盒攻击与协同进化评估研究。

    Paper analysisRead analysis
You have reached the end