Generative Adversarial Examples for Sequential Text Recognition Models with Artistic Text Style

Yanhong Liu, Fengming Cao, Yuqi Zhang

2022

Abstract

The deep neural networks (DNNs) based sequential text recognition (STR) has made great progress in recent years. Although highly related to security issues, STR has been paid rare attention on its weakness and robustness. Most existing studies have generated adversarial examples for DNN models conducting non-sequential prediction tasks such as classification, segmentation, object detection etc. Recently, research efforts have shifted beyond the Lp norm-bounded attack and generated realistic adversarial examples with semantic meanings. We follow this trend and propose a general framework of generating novel adversarial text images for STR models, based on the technique of artistic text style transfer. Experimental results show that our crafted adversarial examples are highly stealthy and the attack success rates for fooling state-of-the-art STR models can achieve up to 100%. Our framework is flexible to create natural adversarial artistic text images with controllable stylistic degree to evaluate the robustness of STR models.

Download


Paper Citation


in Harvard Style

Liu Y., Cao F. and Zhang Y. (2022). Generative Adversarial Examples for Sequential Text Recognition Models with Artistic Text Style. In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-549-4, pages 71-79. DOI: 10.5220/0010866800003122


in Bibtex Style

@conference{icpram22,
author={Yanhong Liu and Fengming Cao and Yuqi Zhang},
title={Generative Adversarial Examples for Sequential Text Recognition Models with Artistic Text Style},
booktitle={Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2022},
pages={71-79},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010866800003122},
isbn={978-989-758-549-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Generative Adversarial Examples for Sequential Text Recognition Models with Artistic Text Style
SN - 978-989-758-549-4
AU - Liu Y.
AU - Cao F.
AU - Zhang Y.
PY - 2022
SP - 71
EP - 79
DO - 10.5220/0010866800003122