Abstract

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.

Highlights

  • With the advent of the Internet, millions of computers became connected, and various applications and services became available through data collection and analysis

  • We propose a method for generating a style-plugged-CAPTCHA image designed to resist recognition by machines while maintaining recognizability to humans, by applying style transfer learning in the CAPTCHA domain

  • We systematically describe the framework of the proposed method, and show that CAPTCHA images of various styles can be generated by applying multiple image styles to the original image

Read more

Summary

Introduction

With the advent of the Internet, millions of computers became connected, and various applications and services became available through data collection and analysis. With the development of various sensors, it became possible to collect information about the physical world. These sensors are usually networked with each other to collect, process, and transmit information. Equipment such as mobile devices collect information using sensors or provide web services to users. It is becoming increasingly important to develop security solutions to defend against automated attacks on mobile devices. Automated public Turing test to tell computers and humans apart (CAPTCHA) [5] is one of the many security solutions for defense against such automated attacks. The method asks a question that is comprehensible by humans

Methods
Discussion
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.