Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter4

Attack type

Jailbreaks7Prompt injection15Poisoning and backdoors35Extraction and theft1Detection evasion32Malicious use3

Impact

Data and privacy leaks57Output manipulation1

System type

Models and APIs1coding agent0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 216papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftImpact：Output manipulationSystem type：Models and APIsSystem type：coding agentClear all

Another 216papers do not have category tags yet and are not included in filtered results.

  1. Analysis and theoryarXiv 2609.33909

    近重复家族干扰精确记录成员推断

    分析近重复族如何让精确记录成员推断误判为入训

    arXiv
    2609.33909
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Pythia-2.8B, GPT-2, Qwen3.5-2B and others5
    Abstract近重复使干净参照 MI 把族级暴露当成精确记录。

    作者研究成员推断能否作为精确记录的数据来源证据。版权和来源审计需要的是该记录本身是否入训，而网页语料中的转载、镜像和轻改会让非同一近重复产生成员样分数。四世界审计用 E 表示精确记录是否入训、用 F 表示其近重复族是否在场，从而分开 H00 到 H10 的标准 MI、H00 到 H01 的族偏移，以及 H01 到 H11 的 exact-given-family。

    Paper analysisRead analysis
You have reached the end