Skip to content

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

Oct 12 · Monday

Backdoors and poisoning · Papers

Found 1 paper
Filter2

Layer

Training and data layer1

System component

Fine-tuning and open weights15Vision1Multimodal6
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：VisionTopic: Backdoors and poisoningClear all
  1. AttacksarXiv 2609.07048

    FreqDoor：面向视觉语言模型的频域后门攻击

    提出 FreqDoor，在频域混合振幅并对生成式 VLM 做训练时视觉后门

    arXiv
    2609.07048
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    BLIP-2 (opt-2.7b), InstructBLIP (flan-t5-xl), LLaVA (interleave-qwen)
    AbstractFreqDoor 用频域振幅混合给三款 VLM 植入仅视觉的训练时后门。

    FreqDoor 是针对生成式 VLM 的仅视觉、训练时后门：在频域混合触发源振幅、保留干净图像相位，使触发在空间上分散。

    Paper analysisRead analysis
You have reached the end