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 surface / entry point

User input7Code repositories and dependencies0Weights and gradients1

Layer

Model layer1

System component

Monitors1Fine-tuning and open weights7Image generation3Multimodal3
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 surface / entry point：Code repositories and dependenciesAttack surface / entry point：Weights and gradientsLayer：Model layerSystem component：MonitorsClear all

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

  1. DefensesarXiv 2608.05578

    AMS 工具通过激活分析检测语言模型的安全训练改动

    提出 AMS，用激活分离与方向相似度检测安全训练改动

    arXiv
    2608.05578
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.2-3B-Instruct, Llama-3.2-1B-Instruct and others14
    AbstractAMS 按激活签名把安全改动分四类，前三类可由两级扫描覆盖，行为微调会漏。

    AMS 是面向开放权重模型、部署前使用的激活扫描器，用来看安全训练被拿掉或改写之后，激活空间里还留着什么几何痕迹。

    Paper analysisRead analysis
You have reached the end