"Invisible Prompts, Visible Threats: Malicious Font Injection in External ..."

Junjie Xiong et al. (2025)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2505.16957

access: open

type: Informal or Other Publication

metadata version: 2025-09-19

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2505-16957
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2505-16957
Junjie Xiong, Changjia Zhu, Shuhang Lin, Chong Zhang, Yongfeng Zhang, Yao Liu, Lingyao Li:
Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models. CoRR abs/2505.16957 (2025)

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.