paperJune 2026Unreviewed

PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation

Leyi Sheng, Han Sun, Zhen Sun, Yuntao Yue, Jinlin Wu, Xinlei He, Jiaheng Wei

Abstract

As Text-to-Image (T2I) jailbreak techniques evolve rapidly, existing benchmarks and reproduction workflows often struggle to keep pace. More importantly, T2I jailbreak evaluation is not a single prompt-level test, but a pipeline-level problem shaped by multiple stages, including prompt transformation, image generation, safety filtering, and multimodal judging. This makes results across papers difficult to reliably reproduce and fairly compare. To bridge this gap, we propose PixJail, a self-evolv

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{sheng2026pixjail,
  title = {{PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation}},
  author = {Leyi Sheng and Han Sun and Zhen Sun and Yuntao Yue and Jinlin Wu and Xinlei He and Jiaheng Wei},
  year = {2026},
  month = jun,
  eprint = {2606.24081},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.24081}
}