"Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal ..."

Shengfang Zhai et al. (2023)

> Home

Details and statistics

DOI: 10.1145/3581783.3612108

access: closed

type: Conference or Workshop Paper

metadata version: 2023-11-09

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/mm/ZhaiDSPF023
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/mm/ZhaiDSPF023
Shengfang Zhai, Yinpeng Dong, Qingni Shen, Shi Pu, Yuejian Fang, Hang Su:
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning. ACM Multimedia 2023: 1577-1587

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.