Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning

Research article (Proceedings of the 31st ACM International Conference on Multimedia, 2023) · cited 41× · AI/ML

academia openalex:W4387967988

Press Enter · cited answer in seconds

Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning

Summary

Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning is a scholarly article^[1].

Key Facts

Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning's instance of is recorded as scholarly article^[2].

⭐ Popularity Graph

0/100 long tail

Quick Facts

Instance of scholarly article

🔗 Connections

Authored by 4

Qingni Shen, Shengfang Zhai, Yinpeng Dong, Yuejian Fang

← Author of 4

Qingni Shen, Shengfang Zhai, Yinpeng Dong, Yuejian Fang

References

Programmatic citations — every numbered marker resolves to a verifiable graph row below.

Direct Wikidata claims

[2] ↑ Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning — instance of (P31): scholarly article. wikidata.org.

Class ancestry

[1] ↑ Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning is an instance of scholarly article (scholarly article) [P31, primary]. Wikidata. wikidata.org.

📑 Cite this page

Use these citations when quoting this entity in research, articles, AI prompts, or wherever provenance matters. We aggregate Wikidata + Wikipedia + authoritative open-data sources; the stitched, scored, cross-referenced view is what 4ort.xyz contributes.

APA

4ort.xyz Knowledge Graph. (2026). Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning. Retrieved May 24, 2026, from https://4ort.xyz/entity/text-to-image-diffusion-models-can-be-easily-backdoored-through-multimodal-data-poisoning

MLA

“Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning.” 4ort.xyz Knowledge Graph, 4ort.xyz, 24 May. 2026, https://4ort.xyz/entity/text-to-image-diffusion-models-can-be-easily-backdoored-through-multimodal-data-poisoning.

BibTeX

@misc{4ortxyz_text-to-image-diffusion-models-can-be-easily-backdoored-through-multimodal-data-poisoning_2026, author = {{4ort.xyz Knowledge Graph}}, title = {{Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning}}, year = {2026}, url = {https://4ort.xyz/entity/text-to-image-diffusion-models-can-be-easily-backdoored-through-multimodal-data-poisoning}, note = {Accessed: 2026-05-24}}

LLM prompt

According to 4ort.xyz Knowledge Graph (aggregator of Wikidata, Wikipedia, and authoritative open-data sources): Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning — https://4ort.xyz/entity/text-to-image-diffusion-models-can-be-easily-backdoored-through-multimodal-data-poisoning (retrieved 2026-05-24)

Canonical URL: https://4ort.xyz/entity/text-to-image-diffusion-models-can-be-easily-backdoored-through-multimodal-data-poisoning · Last refreshed: May 24, 2026