Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter5

Attack type

Prompt injection15Poisoning and backdoors4Detection evasion3Malicious use1

System type

LLM applications1coding agent0science agent0

Attack surface / entry point

User input5Documents and messages1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
Attack type：Malicious useSystem type：LLM applicationsSystem type：coding agentSystem type：science agentAttack surface / entry point：Documents and messagesClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.12448

    GraphProfiler 用个人知识图谱推断敏感属性并溯源到具体帖子

    提出 GraphProfiler，用个人知识图谱从帖子历史推断敏感属性并溯源

    arXiv
    2609.12448
    Published
    Layer
    Application layer
    Setting
    LLM applications
    AbstractGraphProfiler 用源链接个人知识图谱做属性推断，准确率接近文本基线，并把证据定位到少量源帖。

    GraphProfiler 是一个可审计的 LLM 敏感属性画像器：用源链接个人知识图谱，把推断落到具体帖子。

    Paper analysisRead analysis
You have reached the end