FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Research article (Proceedings of the AAAI Conference on Artificial Intelligence, 2025) · cited 33× · AI/ML

academia openalex:W4409348010

Press Enter · cited answer in seconds

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Summary

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts is a scholarly article^[1].

Key Facts

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts's instance of is recorded as scholarly article^[2].

⭐ Popularity Graph

0/100 long tail

Quick Facts

Instance of scholarly article

🔗 Connections

Authored by 7

Anyu Wang, Conglei Wang, Delong Ran, Jinyuan Liu, Tianshuo Cong, Xiaoyun Wang, Yichen Gong

← Author of 7

Anyu Wang, Conglei Wang, Delong Ran, Jinyuan Liu, Tianshuo Cong, Xiaoyun Wang, Yichen Gong

References

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

Direct Wikidata claims

[2] ↑ FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts — instance of (P31): scholarly article. wikidata.org.

Class ancestry

[1] ↑ FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts 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). FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts. Retrieved May 24, 2026, from https://4ort.xyz/entity/figstep-jailbreaking-large-vision-language-models-via-typographic-visual-prompts

MLA

“FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts.” 4ort.xyz Knowledge Graph, 4ort.xyz, 24 May. 2026, https://4ort.xyz/entity/figstep-jailbreaking-large-vision-language-models-via-typographic-visual-prompts.

BibTeX

@misc{4ortxyz_figstep-jailbreaking-large-vision-language-models-via-typographic-visual-prompts_2026, author = {{4ort.xyz Knowledge Graph}}, title = {{FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts}}, year = {2026}, url = {https://4ort.xyz/entity/figstep-jailbreaking-large-vision-language-models-via-typographic-visual-prompts}, note = {Accessed: 2026-05-24}}

LLM prompt

According to 4ort.xyz Knowledge Graph (aggregator of Wikidata, Wikipedia, and authoritative open-data sources): FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts — https://4ort.xyz/entity/figstep-jailbreaking-large-vision-language-models-via-typographic-visual-prompts (retrieved 2026-05-24)

Canonical URL: https://4ort.xyz/entity/figstep-jailbreaking-large-vision-language-models-via-typographic-visual-prompts · Last refreshed: May 24, 2026