Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models

Abstract

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable to jailbreak attacks. A key challenge is that safety behavior learned in the textual space does not reliably transfer to fused cross-modal representations, leaving multimodal inputs exploitable through latent semantic cues. We propose Text-Anchored Semantic Perturbation Attack (TA-SPA), a black-box jailbreak framework that optimizes transferable

Categories

Framework mappings

Suggested from the entry's categories.

@misc{li2026textanchored,
  title = {{Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models}},
  author = {Wenyun Li and Guiping Cao and Xiangyuan Lan and Zheng Zhang},
  year = {2026},
  month = aug,
  eprint = {2608.22312},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.22312}
}