mlsanityData to 7 Oct 2026

Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition

arXiv 2308.02369 ↗First posted 4 Aug 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Optical Character Recognition (OCR) enables automatic text extraction from scanned or digitized text images, but it also makes it easy to pirate valuable or sensitive text from these images. Previous methods to prevent OCR piracy by distorting characters in text images are impractical in real-world scenarios, as pirates can capture arbitrary portions of the text images, rendering the defenses ineffective. In this work, we propose a novel and effective defense mechanism termed the Universal Defensive Underpainting Patch (UDUP) that modifies the underpainting of text images instead of the characters. UDUP is created through an iterative optimization process to craft a small, fixed-size defensive patch that can generate non-overlapping underpainting for text images of any size. Experimental results show that UDUP effectively defends against unauthorized OCR under the setting of any screenshot range or complex image background. It is agnostic to the content, size, colors, and languages of characters, and is robust to typical image operations such as scaling and compressing. In addition, the transferability of UDUP is demonstrated by evading several off-the-shelf OCRs. The code is available at https://github.com/QRICKDD/UDUP.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 4 Aug 2023.

Builds on

19 of 26 references.

References · 19

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  3. 2019Character Region Awareness for Text Detectioncited by 273
  4. 2017EAST: An Efficient and Accurate Scene Text Detectorcited by 248
  5. 2019Real-time Scene Text Detection with Differentiable Binarizationcited by 212
  6. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
  7. 2019Shape Robust Text Detection with Progressive Scale Expansion Networkcited by 147
  8. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  9. 2018TextBoxes++: A Single-Shot Oriented Scene Text Detectorcited by 119
  10. 2019Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Networkcited by 114
  11. 2022Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusioncited by 94
  12. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 92
7 more
  1. 2018Universal Adversarial Trainingcited by 85
  2. 2018NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognitioncited by 73
  3. 2021PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Textcited by 65
  4. 2020MANGO: A Mask Attention Guided One-Stage Scene Text Spottercited by 51
  5. 2021PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Networkcited by 49
  6. 2018Fooling OCR Systems with Adversarial Text Imagescited by 12
  7. 2020Attacking Optical Character Recognition (OCR) Systems with Adversarial Watermarkscited by 7

Built on by

Not cited yet.