paperMarch 2026Unreviewed

SlowBA: An efficiency backdoor attack towards VLM-based GUI agents

Junxian Li, Tu Lan, Haozhen Tan, Yan Meng, Haojin Zhu

Abstract

Modern vision-language-model (VLM) based graphical user interface (GUI) agents are expected not only to execute actions accurately but also to respond to user instructions with low latency. While existing research on GUI-agent security mainly focuses on manipulating action correctness, the security risks related to response efficiency remain largely unexplored. In this paper, we introduce SlowBA, a novel backdoor attack that targets the responsiveness of VLM-based GUI agents. The key idea is to

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{li2026slowba,
  title = {{SlowBA: An efficiency backdoor attack towards VLM-based GUI agents}},
  author = {Junxian Li and Tu Lan and Haozhen Tan and Yan Meng and Haojin Zhu},
  year = {2026},
  month = mar,
  eprint = {2603.08316},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.08316}
}