paperMay 2026Unreviewed

CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models

Ji Guo, Xiaolong Qin, Cencen Liu, Jielei Wang, Jierun Chen, Wenbo Jiang

Abstract

Vision-Language Models (VLMs) have achieved remarkable success in tasks such as image captioning and visual question answering (VQA). However, as their applications become increasingly widespread, recent studies have revealed that VLMs are vulnerable to backdoor attacks. Existing backdoor attacks on VLMs primarily rely on data poisoning by adding visual triggers and modifying text labels, where the induced image-text mismatch makes poisoned samples easy to detect. To address this limitation, we

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{guo2026cbv,
  title = {{CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models}},
  author = {Ji Guo and Xiaolong Qin and Cencen Liu and Jielei Wang and Jierun Chen and Wenbo Jiang},
  year = {2026},
  month = may,
  eprint = {2605.02202},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.02202}
}