Detail publikace

SEMI-SUPERVISED DEEP LEARNING APPROACH FOR BREAKING GEOCACHING CAPTCHAS

BOŠTÍK, O.

Originální název

SEMI-SUPERVISED DEEP LEARNING APPROACH FOR BREAKING GEOCACHING CAPTCHAS

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

For nearly two decades, a substantial part of developed anti-abuse and anti-spam systems for web applications called CAPTCHA is based on imperfections in OCR (Optical Character Recognition) algorithms. But with improvements in Deep Learning in OCR, these systems are now obsolete. More and more systems can now break various text Captchas with great accuracy. Now with sufficient training dataset, almost every text-based Captcha scheme can be broken. The focus of this work is to present an idea of a semi-supervised method for reading text-based Captcha which needs only a small initial dataset. The main part of this article is dealing with the problem of training a deep learning system with only a small sample of target Captcha scheme via transfer learning.

Klíčová slova

OCR, CAPTCHA, Deep learning, semi-supervised learning, MATLAB

Autoři

BOŠTÍK, O.

Vydáno

23. 4. 2020

Nakladatel

Vysoké učené Technické, Fakulta elektrotechniky a komunikačních technologií

Místo

Brno

ISBN

978-80-214-5868-0

Kniha

Proceedings II of the 26th Conference STUDENT EEICT 2020 - Selected papers

Edice

1

Číslo edice

1

Strany od

166

Strany do

170

Strany počet

5

BibTex

@inproceedings{BUT164004,
  author="Ondřej {Boštík}",
  title="SEMI-SUPERVISED DEEP LEARNING APPROACH FOR BREAKING GEOCACHING CAPTCHAS",
  booktitle="Proceedings II of the 26th Conference STUDENT EEICT 2020 - Selected papers",
  year="2020",
  series="1",
  number="1",
  pages="166--170",
  publisher="Vysoké učené Technické, Fakulta elektrotechniky a komunikačních technologií",
  address="Brno",
  isbn="978-80-214-5868-0"
}