Skip to content

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

Oct 12 · Monday

Backdoors and poisoning · Papers

Found 2 papers
Filter2

Layer

Training and data layer2

System component

Fine-tuning and open weights15Audio2Multimodal6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Layer：Training and data layerSystem component：AudioTopic: Backdoors and poisoningClear all
  1. AttacksarXiv 2610.09819

    FAB 攻击：给 HuBERT/WavLM 植入后门，背景警笛声即可让下游语音任务失灵

    提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门

    arXiv
    2610.09819
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    HuBERT-base, WavLM-base

    Abstract论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。

    Paper analysisRead analysis
You have reached the end