MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models

Abstract

Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge. While prior work has shown that structured visual prompts such as flowcharts can effectively jailbreak VLMs, existing studies are largely limited to English-centric settings. In this paper, we introduce MLingualFC, a multilingual multimodal benchmark designed to evaluate jailbreak vulnerabilities of VLMs across diverse languages using structured flowc

Categories

Framework mappings

Suggested from the entry's categories.

@misc{makwana2026mlingualfc,
  title = {{MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models}},
  author = {Rishabh Makwana and Mamta and Deeksha Varshney and Oana Cocarascu},
  year = {2026},
  month = jun,
  eprint = {2606.07706},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.07706}
}