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

Jailbreaks13Poisoning and backdoors1Extraction and theft5Detection evasion8Malicious use5

Layer

Model layer1Application layer52Training and data layer11

System component

Memory0Monitors0Fine-tuning and open weights3Multimodal1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：Poisoning and backdoorsLayer：Model layerSystem component：MemorySystem component：MonitorsSystem component：MultimodalClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.39548

    NDDL：用正常扩散动力学为文生图模型做后门防御

    提出 NDDL，用良性扩散轨迹检测文生图后门提示并定位触发 token

    arXiv
    2609.39548
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Stable Diffusion v1.5, Stable Diffusion XL, Stable Diffusion v3.5 and others4
    AbstractNDDL 从良性扩散轨迹学习正常转移，用动态不一致检测后门并定位触发 token。

    NDDL 是面向文生图扩散模型的后门防御：防御者只有白盒模型访问和良性提示词，没有后门先验，需要区分后门提示词并找出触发 token。

    Paper analysisRead analysis
You have reached the end