SEMI-SUPERVISED DEEP LEARNING APPROACH FOR BREAKING GEOCACHING CAPTCHAS

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F20%3APU136492" target="_blank" >RIV/00216305:26220/20:PU136492 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
SEMI-SUPERVISED DEEP LEARNING APPROACH FOR BREAKING GEOCACHING CAPTCHAS
Original language description
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.
Czech name
—
Czech description
—

Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings II of the 26th Conference STUDENT EEICT 2020 - Selected papers
ISBN
978-80-214-5868-0
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
166-170
Publisher name
Vysoké učené Technické, Fakulta elektrotechniky a komunikačních technologií
Place of publication
Brno
Event location
BRNO
Event date
Apr 23, 2020
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
000598376500039

Similar results(10)