• čeština
    • English
    • русский
    • Deutsch
    • français
    • polski
    • українська
  • English 
    • čeština
    • English
    • русский
    • Deutsch
    • français
    • polski
    • українська
  • Login
View Item 
  •   Repository Home
  • Publikační činnost pracovníků VUT v Brně
  • Fakulta elektrotechniky a komunikačních technologií
  • Ústav automatizace a měřicí techniky
  • View Item
  •   Repository Home
  • Publikační činnost pracovníků VUT v Brně
  • Fakulta elektrotechniky a komunikačních technologií
  • Ústav automatizace a měřicí techniky
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Semi-supervised deep learning approach to break common CAPTCHAs

Thumbnail
View/Open
05957_accepted.pdf (371.0Kb)
Date
2021-04-12
Author
Boštík, Ondřej
Horák, Karel
Kratochvíla, Lukáš
Zemčík, Tomáš
Bilík, Šimon
Altmetrics
10.1007/s00521-021-05957-0
Metadata
Show full item record
Abstract
Manual data annotation is a time consuming activity. A novel strategy for automatic training of the CAPTCHA breaking system with no manual dataset creation is presented in this paper. We demonstrate the feasibility of the attack against a text-based CAPTCHA scheme utilizing similar network infrastructure used for Denial of Service attacks. The main goal of our research is to present a possible vulnerability in CAPTCHA systems when combining the brute-force attack with transfer learning. The classification step utilizes a simple convolutional neural network with 15 layers. Training stage uses automatically prepared dataset created without any human intervention and transfer learning for fine-tuning the deep neural network classifier. The designed system for breaking text-based CAPTCHAs achieved 80% classification accuracy after 6 fine-tuning steps for a 5 digit text-based CAPTCHA system. The results presented in this paper suggest, that even the simple attack with a large number of attacking computers can be an effective alternative to current CAPTCHA breaking systems.
Keywords
CAPTCHA, Semi-supervised learning, Convolutional Neural Networks
Persistent identifier
http://hdl.handle.net/11012/203005
Document type
Peer reviewed
Document version
Postprint
Fulltext will be available on 13. 04. 2022
Source
NEURAL COMPUTING & APPLICATIONS. 2021, vol. 33, issue 20, p. 13333-13343.
https://link.springer.com/article/10.1007%2Fs00521-021-05957-0
DOI
10.1007/s00521-021-05957-0
Collections
  • Ústav automatizace a měřicí techniky [81]
Citace PRO

Portal of libraries | Central library on Facebook
DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback | Theme by @mire NV
 

 

Browse

All of repositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

LoginRegister

Statistics

View Usage Statistics

Portal of libraries | Central library on Facebook
DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback | Theme by @mire NV