paperAugust 2026Unreviewed

Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

Benlei Cui, Shen Pang, Yuke Wang, Xuemei Dong, Yuwen Zhai, Jingqun Tang, Haiyang Yu, Hui Xue, Longtao Huang, Haiwen Hong

View resource PDF

Abstract

The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based attacks freeze the image-text layout, while iterative attacks adapt only the image-text content with fixed attack strategies and frozen attacker parameters. We propose Meta-Adaptive Multimodal Jailbreaking (MAMJ), which instead optimizes the attacker itself along two axes: an attack strategy prompt (ASP) governing attack i

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{cui2026fully,
  title = {{Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models}},
  author = {Benlei Cui and Shen Pang and Yuke Wang and Xuemei Dong and Yuwen Zhai and Jingqun Tang and Haiyang Yu and Hui Xue and Longtao Huang and Haiwen Hong},
  year = {2026},
  month = aug,
  eprint = {2608.27531},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.27531}
}