ML Anthology

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

Yichen Gong, Delong Ran, Jinyuan Liu, Conglei Wang, Tianshuo Cong, Anyu Wang, Sisi Duan, Xiaoyun Wang
AAAI 2025 pp. 23951-23959
doi:10.1609/AAAI.V39I22.34568 /aaai/2025/gong2025aaai-figstep/
AAAI Semantic Scholar

Cite

Text

Gong et al. "FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I22.34568

Markdown

[Gong et al. "FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/gong2025aaai-figstep/) doi:10.1609/AAAI.V39I22.34568

BibTeX

@inproceedings{gong2025aaai-figstep,
  title     = {{FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts}},
  author    = {Gong, Yichen and Ran, Delong and Liu, Jinyuan and Wang, Conglei and Cong, Tianshuo and Wang, Anyu and Duan, Sisi and Wang, Xiaoyun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {23951-23959},
  doi       = {10.1609/AAAI.V39I22.34568},
  url       = {https://mlanthology.org/aaai/2025/gong2025aaai-figstep/}
}