Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Attack type

Poisoning and backdoors21Extraction and theft1Detection evasion0

Attack technique

Gradient and representation optimization0Dormant triggers1

Layer

Prompt layer7Application layer4Training and data layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack type：Detection evasionAttack technique：Gradient and representation optimizationAttack technique：Dormant triggersLayer：Training and data layerClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.33985

    研究：众包微调数据投毒可放大专有指令抽取

    提出主题锚点投毒，放大众包微调后的专有指令提取

    arXiv
    2609.33985
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct, Llama-3.1-8B-Instruct and others4

    Abstract论文提出基于主题锚点的数据中毒攻击，证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。

    Paper analysisRead analysis
You have reached the end