paperAugust 2026Unreviewed

Adversarial Attacks on Deep OCR Systems

Wenbo Sun, Hong-Zong Li, Yanyun Wang, Jia-Hao Ma, Shuxin Zhuang, Rong Feng, Shi-Qin Tang, Zi Liang

Abstract

Deep-OCR (DeepSeek-OCR) advances document recognition by treating the visual modality as an optical compression medium, enabling long-context OCR at low token cost. However, its increased complexity may introduce new security vulnerabilities. In this paper, we present, to the best of our knowledge, the first pure black-box adversarial attack against a generative OCR vision-language model, where only the decoded string can be queried and no gradients, logits, or model internals are available. We

Framework mappings

MITRE ATLAS

AML.T0043Craft Adversarial Data

Suggested from the entry's categories.

Cite

@misc{sun2026adversarial,
  title = {{Adversarial Attacks on Deep OCR Systems}},
  author = {Wenbo Sun and Hong-Zong Li and Yanyun Wang and Jia-Hao Ma and Shuxin Zhuang and Rong Feng and Shi-Qin Tang and Zi Liang},
  year = {2026},
  month = aug,
  eprint = {2608.07636},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/949627af3c2bcd16e81a3c0d9d82bf097b7b3bce}
}