Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Attack type

Prompt injection3Poisoning and backdoors1

Attack technique

Dormant triggers10Selection manipulation1

Impact

Unauthorized actions3Data and privacy leaks1Output manipulation4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack type：Poisoning and backdoorsAttack technique：Selection manipulationImpact：Data and privacy leaksClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2608.25776

    EvoMal 攻击利用自我进化编码 Agent 的自我投毒实现蠕虫式传播

    提出 EVOMAL，诱导自演化编码 Agent 在创建技能时自我投毒并蠕虫传播

    arXiv
    2608.25776
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Devstral-Small-2, Gemma-4-31B-IT, Qwen3-Coder-Next and others7

    Abstract论文指出了自演化智能体模仿检索代码的自我毒化漏洞，提出 EVOMAL 攻击与防御，阐明了供应链新风险。

    Paper analysisRead analysis
You have reached the end