CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks

Mobile devices such as sensors are used to connect to the Internet and provide services to users. Web services are vulnerable to automated attacks, which can restrict mobile devices from accessing websites. To prevent such automated attacks, CAPTCHAs are widely used as a security solution. However,...

Full description

Bibliographic Details
Main Authors: Hyun Kwon, Hyunsoo Yoon, Ki-Woong Park
Format: Article
Language:English
Published: MDPI AG 2020-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/20/5/1495
_version_ 1798005522678415360
author Hyun Kwon
Hyunsoo Yoon
Ki-Woong Park
author_facet Hyun Kwon
Hyunsoo Yoon
Ki-Woong Park
author_sort Hyun Kwon
collection DOAJ
description Mobile devices such as sensors are used to connect to the Internet and provide services to users. Web services are vulnerable to automated attacks, which can restrict mobile devices from accessing websites. To prevent such automated attacks, CAPTCHAs are widely used as a security solution. However, when a high level of distortion has been applied to a CAPTCHA to make it resistant to automated attacks, the CAPTCHA becomes difficult for a human to recognize. In this work, we propose a method for generating a CAPTCHA image that will resist recognition by machines while maintaining its recognizability to humans. The method utilizes the style transfer method, and creates a new image, called a style-plugged-CAPTCHA image, by incorporating the styles of other images while keeping the content of the original CAPTCHA. In our experiment, we used the TensorFlow machine learning library and six CAPTCHA datasets in use on actual websites. The experimental results show that the proposed scheme reduces the rate of recognition by the DeCAPTCHA system to 3.5% and 3.2% using one style image and two style images, respectively, while maintaining recognizability by humans.
first_indexed 2024-04-11T12:40:37Z
format Article
id doaj.art-15f684b3634c44e1a8f1cc45f072f8b9
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-04-11T12:40:37Z
publishDate 2020-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-15f684b3634c44e1a8f1cc45f072f8b92022-12-22T04:23:29ZengMDPI AGSensors1424-82202020-03-01205149510.3390/s20051495s20051495CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural NetworksHyun Kwon0Hyunsoo Yoon1Ki-Woong Park2Department of Electrical Engineering, Korea Military Academy, Seoul 01805, KoreaSchool of Computing, Korea Advanced Institute of Science and Technology, Daejeon 34141, KoreaDepartment of Computer and Information Security, Sejong University, Seoul 05006, KoreaMobile devices such as sensors are used to connect to the Internet and provide services to users. Web services are vulnerable to automated attacks, which can restrict mobile devices from accessing websites. To prevent such automated attacks, CAPTCHAs are widely used as a security solution. However, when a high level of distortion has been applied to a CAPTCHA to make it resistant to automated attacks, the CAPTCHA becomes difficult for a human to recognize. In this work, we propose a method for generating a CAPTCHA image that will resist recognition by machines while maintaining its recognizability to humans. The method utilizes the style transfer method, and creates a new image, called a style-plugged-CAPTCHA image, by incorporating the styles of other images while keeping the content of the original CAPTCHA. In our experiment, we used the TensorFlow machine learning library and six CAPTCHA datasets in use on actual websites. The experimental results show that the proposed scheme reduces the rate of recognition by the DeCAPTCHA system to 3.5% and 3.2% using one style image and two style images, respectively, while maintaining recognizability by humans.https://www.mdpi.com/1424-8220/20/5/1495machine learningneural networkimage style transfercaptchaconvolutional neural network (cnn)
spellingShingle Hyun Kwon
Hyunsoo Yoon
Ki-Woong Park
CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks
Sensors
machine learning
neural network
image style transfer
captcha
convolutional neural network (cnn)
title CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks
title_full CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks
title_fullStr CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks
title_full_unstemmed CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks
title_short CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks
title_sort captcha image generation two step style transfer learning in deep neural networks
topic machine learning
neural network
image style transfer
captcha
convolutional neural network (cnn)
url https://www.mdpi.com/1424-8220/20/5/1495
work_keys_str_mv AT hyunkwon captchaimagegenerationtwostepstyletransferlearningindeepneuralnetworks
AT hyunsooyoon captchaimagegenerationtwostepstyletransferlearningindeepneuralnetworks
AT kiwoongpark captchaimagegenerationtwostepstyletransferlearningindeepneuralnetworks