Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Model risks

Hallucination and fabrication1

System type

Models and APIs0coding agent1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Model risks：Hallucination and fabricationSystem type：Models and APIsSystem type：coding agentClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2607.12340

    Research: LLM agent skill-name hallucination rates reach up to 62%, which can be exploited via squatting for supply-chain attacks

    提出技能名称抢注攻击，利用 Agent 虚构技能名实施供应链劫持

    arXiv
    2607.12340
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GLM-4.5-Air, GPT-5.4-mini, Claude Sonnet 4.6 and others12
    Abstract研究证实智能体虚构技能名具有高发生率与可预测性，现有防御难以兼顾安全与效用，亟需注册表结构性防护。

    本研究系统揭示了大模型智能体技能推荐场景下的虚构技能名称安全风险，将其形式化为一种新型供应链抢注攻击。

    Paper analysisRead analysis
You have reached the end