Scholarlink

<p>In the era of deep learning, Scene Text Recognition (STR) has become a vital technology for extracting textual information from natural images, with broad practical applications (e.g., autonomous driving). Nevertheless, STR models remain susceptible to adversarial attacks, which could be used to help enhance the robustness of STR models. Current attack strategies for STR typically generate adversarial examples on a per-image basis, often requiring too many queries or the full knowledge of the target model. From a practical standpoint, the implementation of these existing methods poses significant challenges. To solve the above-mentioned problems, this paper introduces a novel universal adversarial attack method designed for STR models. By incorporating a modified saliency map approach and aggregating saliency information across multiple samples, we generate universal adversarial perturbations (UAP) that effectively deceive STR models. Experimental results show that the proposed method achieves a high attack success rate and exhibits strong transferability across different models, even in a black-box setting.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Beyond single image: modified saliency aggregation for universal attacks on STR models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月25日

查看全文
  • Yikun Xu,
  • Peibin Chen,
  • Junfeng Xu,
  • Wanshan Xu,
  • Pengwen Dai

摘要

In the era of deep learning, Scene Text Recognition (STR) has become a vital technology for extracting textual information from natural images, with broad practical applications (e.g., autonomous driving). Nevertheless, STR models remain susceptible to adversarial attacks, which could be used to help enhance the robustness of STR models. Current attack strategies for STR typically generate adversarial examples on a per-image basis, often requiring too many queries or the full knowledge of the target model. From a practical standpoint, the implementation of these existing methods poses significant challenges. To solve the above-mentioned problems, this paper introduces a novel universal adversarial attack method designed for STR models. By incorporating a modified saliency map approach and aggregating saliency information across multiple samples, we generate universal adversarial perturbations (UAP) that effectively deceive STR models. Experimental results show that the proposed method achieves a high attack success rate and exhibits strong transferability across different models, even in a black-box setting.