paperSeptember 2026Unreviewed

InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models

Chengyin Hu, Ding-Yi Lu, Jiajun Han, Xiang Chen, Weiwen Shi, Jiahuan Long, Yiwei Wei, Jiu-Jiang Guo

Abstract

Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception under low-visibility conditions, yet their robustness to targeted adversarial attacks remains poorly understood. Existing adversarial patch methods mainly study RGB-based models or a single downstream task and do not characterize whether localized perturbations can induce an intended semantic target in IR-VLMs. We propose InfraPatch, a white-box, per-instance framework for targeted digital gr

Framework mappings

MITRE ATLAS

AML.T0043Craft Adversarial Data

Suggested from the entry's categories.

Cite

@misc{hu2026infrapatch,
  title = {{InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models}},
  author = {Chengyin Hu and Ding-Yi Lu and Jiajun Han and Xiang Chen and Weiwen Shi and Jiahuan Long and Yiwei Wei and Jiu-Jiang Guo},
  year = {2026},
  month = sep,
  eprint = {2609.02233},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/286d27171af8b29fb92ec42d28ea825cb62a78eb}
}