paperApril 2026Unreviewed

Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers

Jiancheng Wang, Lidan Liang, Yong Wang, Zengzhen Su, Haifeng Xia, Yuanting Yan, Wei Wang

Abstract

Visual language model (VLM) is rapidly being integrated into safety-critical systems such as autonomous driving, making it an important attack surface for potential backdoor attacks. Existing backdoor attacks mainly rely on unimodal, explicit, and easily detectable triggers, making it difficult to construct both covert and stable attack channels in autonomous driving scenarios. GLA introduces two naturalistic triggers: graffiti-based visual patterns generated via stable diffusion inpainting, whi

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data

Suggested from the entry's categories.

Cite

@misc{wang2026multimodal,
  title = {{Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers}},
  author = {Jiancheng Wang and Lidan Liang and Yong Wang and Zengzhen Su and Haifeng Xia and Yuanting Yan and Wei Wang},
  year = {2026},
  month = apr,
  eprint = {2604.04630},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.04630}
}