Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack type

Jailbreaks7Model tampering6Extraction and theft3Detection evasion7Malicious use0

Impact

Data and privacy leaks3

System type

Models and APIs3

Attacker access

Black-box15Gray-box3White-box3

Attack surface / entry point

Weights and gradients3

Layer

Model layer3Application layer0Training and data layer3
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：Malicious useAttacker access：White-boxLayer：Application layerLayer：Training and data layerClear all

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

  1. AttacksarXiv 2610.01365

    ReGap：无需真实隐私数据即可通过微调重新提取模型隐私关联

    提出 ReGap，用自生成伪监督微调恢复模型中的隐私关联

    arXiv
    2610.01365
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box, Gray-box
    Evaluated models
    GPT-2 Small, GPT-2 Medium, GPT-2 Large and others6

    Abstract提出无真实私有监督的恢复攻击 ReGap，实验显示微调可通过自生成数据唤醒模型潜在隐私关联，突显后适应隐私风险。

    Paper analysisRead analysis
  3. AttacksarXiv 2609.04382

    研究揭示 split-LLM 训练中返回梯度泄露真实行，前向隐私门仍通过

    揭示拆分训练返回梯度以零支撑暴露诱饵行并泄露训练内容

    arXiv
    2609.04382
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Qwen3-0.6B, 35B-A3B
    Abstract论文揭示拆分训练中反向梯度零支撑完全暴露诱饵行，联合视图突破门控，裁剪加噪可有效缓解。

    这是一项关于双节点大语言模型拆分训练系统的系统安全案例研究，揭示了评估工具遗漏反向信道所导致的静默隐私失效。

    Paper analysisRead analysis
You have reached the end