Cross-Modal Backdoors in Multimodal Large Language Models

Runhe Wang, Li Bai, Haibo Hu, Songze Li

Abstract

Developers increasingly construct multimodal large language models (MLLMs) by assembling pretrained components,introducing supply-chain attack surfaces.Existing security research primarily focuses on poisoning backbones such as encoders or large language models (LLMs),while the security risks of lightweight connectors remain unexplored.In this work,we propose a novel cross-modal backdoor attack that exploits this overlooked vulnerability.By poisoning only the connector using a single seed sample

Categories

Cite This Resource

@article{llmsec202600136,
  title = {Cross-Modal Backdoors in Multimodal Large Language Models},
  author = {Runhe Wang and Li Bai and Haibo Hu and Songze Li},
  year = {2026},
  url = {https://arxiv.org/abs/2605.07490},
}