paperJuly 2026Unreviewed

Open Models, Open Risks: Measuring Unsafe Generation in Text-to-Image Models In the Wild

Peilin Han, Yang Liu, Yilong Yang, Jingchun Zhang, Teng Li, Jianfeng Ma, Zhuo Ma

Abstract

Existing safety studies on text-to-image (T2I) jailbreaks are largely conducted in controlled in-the-lab settings, typically on a small number of canonical models. As a result, the current safety status of the rapidly growing in-the-wild T2I ecosystem remains unclear. This uncertainty is amplified by two factors: existing detector-based metrics are designed for controlled evaluation, and in-the-wild risks may arise not only from adversarial prompting, but also from unsafe release practices and u

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{han2026open,
  title = {{Open Models, Open Risks: Measuring Unsafe Generation in Text-to-Image Models In the Wild}},
  author = {Peilin Han and Yang Liu and Yilong Yang and Jingchun Zhang and Teng Li and Jianfeng Ma and Zhuo Ma},
  year = {2026},
  month = jul,
  eprint = {2607.07827},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.07827}
}