Attacking Optical Character Recognition (OCR) Systems with Adversarial Watermarks

02/08/2020
by   Lu Chen, et al.
17

Optical character recognition (OCR) is widely applied in real applications serving as a key preprocessing tool. The adoption of deep neural network (DNN) in OCR results in the vulnerability against adversarial examples which are crafted to mislead the output of the threat model. Different from vanilla colorful images, images of printed text have clear backgrounds usually. However, adversarial examples generated by most of the existing adversarial attacks are unnatural and pollute the background severely. To address this issue, we propose a watermark attack method to produce natural distortion that is in the disguise of watermarks and evade human eyes' detection. Experimental results show that watermark attacks can yield a set of natural adversarial examples attached with watermarks and attain similar attack performance to the state-of-the-art methods in different attack scenarios.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/15/2020

FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems

Deep neural networks (DNNs) significantly improved the accuracy of optic...
research
02/15/2018

Fooling OCR Systems with Adversarial Text Images

We demonstrate that state-of-the-art optical character recognition (OCR)...
research
01/13/2023

On the feasibility of attacking Thai LPR systems with adversarial examples

Recent advances in deep neural networks (DNNs) have significantly enhanc...
research
08/30/2022

A Black-Box Attack on Optical Character Recognition Systems

Adversarial machine learning is an emerging area showing the vulnerabili...
research
05/31/2018

Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data

We present a probabilistic framework for studying adversarial attacks on...
research
05/20/2021

Simple Transparent Adversarial Examples

There has been a rise in the use of Machine Learning as a Service (MLaaS...
research
06/30/2021

Understanding Adversarial Examples Through Deep Neural Network's Response Surface and Uncertainty Regions

Deep neural network (DNN) is a popular model implemented in many systems...

Please sign up or login with your details

Forgot password? Click here to reset